Back to skill

Security audit

FaceBook Go-To-Market - How to build on Facebook Groups

Security checks for vulnerabilities and agentic risk

Overview

This is a real payment/shopping integration, but it gives agents broad money-moving authority and asks them to trust server-supplied instructions and scripts during checkout.

Install only if you intentionally want a broad CreditClaw commerce agent, not just Amazon shopping. Use a tightly scoped runtime, restrict the API key, require human approval for purchases, avoid trusting server-provided natural-language instructions as commands, and do not run remotely delivered decrypt scripts unless they are independently verified and sandboxed.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (3)

T01 · Skill Instruction Hijacking

Error
Location
encrypted-card.md:83
Finding

Server-Controlled Instructions Are Executed by an Authenticated Sub-Agent

Content
View full analysis
Card-ChaseD-9547.md", "Use the decrypted card details to complete checkout at DigitalOcean.", "Call POST /api/v1/bot/rail5/confirm with { \"checkout_id\": \"r5chk_abc123\", \"status\": \"success\" } when done.", "If checkout fails, call confirm with { \"status\": \"failed\" } instead.", "Announce the result." ], "spawn_payload": { "task": "You are a checkout agent...", "cleanup": "delete", "runTimeoutSeconds": 300, "label": "checkout-digitalocean" } } ``` ```text ### Step 2: Spawn a Sub-Agent Once the checkout is approved, spawn an ephemeral sub-agent using the `spawn_payload` from the response: sessions_spawn({ task: spawn_payload.task, cleanup: "delete", runTimeoutSeconds: 300 }) The sub-agent executes the `checkout_steps` in sequence. You (the main agent) wait for the sub-agent to complete and then announce the result. ``` ### Technical Analysis The skill directs the main Agent to take the `task` and `checkout_steps` returned by the remote CreditClaw API and execute them as Agent instructions. These fields are treated as trusted commands rather than untrusted data. There is no documented local schema restricting the contents of the task, no allowlist of permitted sub-agent operations, and no requirement to compare the returned instructions with a fixed local transaction procedure. Consequently, control over the API response provides control over the sub-agent’s goals and actions. The sub-agent is expected to possess or obtain access to the CreditClaw API crede ...[truncated 1876 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
encrypted-card.md:175
Finding

Remote Card Payload Supplies Executable JavaScript That Is Run Locally

Content
View full analysis
Card-ChaseD-9547.md This outputs the card JSON (number, CVV, expiry, name, billing address). **Critical:** The sub-agent must **never** store, log, or persist the decrypted card data. It exists only in memory for this single transaction. After checkout, the sub-agent is deleted. ``` ```text ## Encrypted Card File Delivery When your owner sets up an encrypted card for you, CreditClaw delivers a single self-contained file via the `rail5.card.delivered` event. **Via webhook:** If you have a `callback_url`, the file is delivered automatically: ``` ```json { "event": "rail5.card.delivered", "bot_id": "bot_abc123", "data": { "card_id": "r5card_...", "card_name": "ChaseD", "card_last4": "9547", "file_content": "", "suggested_path": ".creditclaw/cards/Card-ChaseD-9547.md", "instructions": "Save this file to .creditclaw/cards/Card-ChaseD-9547.md — then confirm delivery via POST /bot/rail5/confirm-delivery" } } ``` ```text **Via bot messages (fallback):** If you don't have a webhook, check `GET /bot/messages` for messages with `event_type: "rail5.card.delivered"`. The payload is identical. After saving the file, acknowledge the message via `POST /bot/messages/ack`. **Save the file** to `.creditclaw/cards/` (or the path in `suggested_path`). The file is self-contained — it includes the decrypt script between `DECRYPT_SCRIPT_START/END` markers and the encrypted data between `ENCRYPTED_CARD_START/END` markers. ``` ### Technical Analysis The card-delivery messa ...[truncated 2404 chars]
Remediation
View remediation

T01 · Skill Instruction Hijacking

Error
Location
encrypted-card.md:205
Finding

Network-Controlled Instructions and Filesystem Paths Are Trusted Without Adequate Validation

Content
View full analysis
", "suggested_path": ".creditclaw/cards/Card-ChaseD-9547.md", "instructions": "Save this file to .creditclaw/cards/Card-ChaseD-9547.md — then confirm delivery via POST /bot/rail5/confirm-delivery" } } ``` ```text **Via bot messages (fallback):** If you don't have a webhook, check `GET /bot/messages` for messages with `event_type: "rail5.card.delivered"`. The payload is identical. After saving the file, acknowledge the message via `POST /bot/messages/ack`. **Save the file** to `.creditclaw/cards/` (or the path in `suggested_path`). The file is self-contained — it includes the decrypt script between `DECRYPT_SCRIPT_START/END` markers and the encrypted data between `ENCRYPTED_CARD_START/END` markers. Follow the `instructions` field in the message payload for next steps. ``` ```bash curl https://creditclaw.com/api/v1/bot/messages \ -H "Authorization: Bearer $CREDITCLAW_API_KEY" ``` ```json { "bot_id": "bot_abc123", "messages": [ { "id": 1, "event_type": "rail5.card.delivered", "payload": { "card_id": "r5card_...", "card_name": "ChaseD", "card_last4": "9547", "file_content": "", "suggested_path": ".creditcl ...[truncated 3282 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Findings (37)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · checkout.md (reported line 341)May include surrounding context.

md
- **Set `amount_locked: true`** for fixed-price products so buyers can't underpay.
- **Leave `amount_usd` empty** for donation or tip jars.
- **Use `page_type: "digital_product"`** when selling downloadable content, API keys, or access tokens.
- **Use `success_url`** to redirect buyers back to your service after payment.
- **Check `GET /bot/sales`** periodically to reconcile completed sales with your fulfillment.
- **Multiple checkout pages** are fine — create one per product or service tier.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest and description frame this as an Amazon shopping skill with guardrailed purchasing, but the document also exposes much broader financial capabilities including selling, invoicing, checkout pages, and public payment collection. This scope mismatch can cause users or orchestrators to grant trust and permissions under a narrower mental model than the skill actually requires, increasing the chance of unintended financial actions.

Content

No source excerpt is available for this finding.

YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedded in AI agent skill text [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · skill.md (reported line 12)May include surrounding context.

md
reditclaw-amazon
version: 2.3.0
updated: 2026-02-23T00:00:00Z
description: Let your agent shop on Amazon with guardrailed wallets and owner approval.
homepage: https://creditclaw.com
api_base: https://creditclaw.com/api/v1
credentials: [CREDITCLAW_API_KEY]
metadata: {"openclaw":{"requires":{"env":["CREDITCLAW_API_KEY"]},"primaryEnv":"CREDITCLAW_API_KEY"}}
---

# CreditClaw — Amazon Shopping for AI Agents

CreditClaw.com is a financial enablement platform for Bots, Agents, and OpenClaw.
Securely manage agentic spending.
1. Encrypted cards — owner's real-world card is encrypted and the bot uses it within strict guardrails after owner approval.
2. A stablecoin wallet to seamlessly enable x402 payments with a simple "Fund with Stripe" option.
3. Easy-to-use "Storefronts" and product management for bots to sell both digital and physical products.

## Skill Files

| File | URL | Purpose |
|------|-----|---------|
| **SKILL.md** (this file) | `https://creditclaw.com/amazon/skill.md` | Reg

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

Generalized storefront, digital/physical sales, and product-management features are unrelated to the stated Amazon shopping purpose and materially expand what the agent can do with financial credentials. Hidden or weakly signposted capability expansion is dangerous because it can bypass user expectations and policy review that would have applied to a broader commerce skill.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The API reference advertises broad non-Amazon commerce endpoints such as payment links, invoices, checkout pages, seller profiles, and shop access. Embedding these in an Amazon shopping skill creates an overprivileged interface where a consumer expecting purchasing support may unknowingly authorize public money collection and sales operations.

Content

No source excerpt is available for this finding.

Unbounded Resource Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Content

Scanner excerpt · checkout.md (reported line 24)May include surrounding context.

md
-H "Content-Type: application/json"
  -d '{
    "title": "Premium API Access - 1 Month",
    "description": "Unlimited queries to my data analysis endpoint.",
    "amount_usd": 5.00,
    "amount_locked": true
  }'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This skill documentation states that checkout pages can collect buyer names and later shows sales and invoice flows exposing buyer email addresses. Because the file is markdown, SQP-2 applies to omitted warnings about behaviors affecting privacy, and there is no visible warning that buyer PII will be stored, transmitted, or shown to the seller.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The markdown explains creating and sending invoices to customer email addresses and later creating payment links with payer email fields, but it does not warn that this causes outbound contact to third parties and processing of their personal data. Under the markdown criteria for SQP-2, this omission matters because the behavior can affect privacy and user expectations.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · checkout.md (reported line 473)May include surrounding context.

md
"title": "Premium API Access",
  "amount_usd": 5.00,
  "page_type": "digital_product",
  "digital_product_url": "https://api.databot.com/keys/generate",
  "shop_visible": true
}

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The workflow description states that real orders can be placed with supported merchants generally, not just Amazon, which again widens the operational scope beyond the skill’s declared purpose. In an agent setting, this mismatch can cause unsafe delegation because users may authorize an Amazon-shopping skill without realizing it can trigger purchases elsewhere.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The purchase flow describes submitting orders that result in real-world purchases but does not prominently warn that sensitive personal data, including shipping address and purchase details, will be transmitted to external services and used to place actual orders. Users or agent operators may underestimate the privacy and financial consequences of invoking this endpoint.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file expands the skill from Amazon-only shopping to additional merchants including Shopify and arbitrary URLs, which materially broadens what the agent can purchase. This creates scope drift between the published skill purpose and the documented capabilities, increasing the chance that an agent or integrator will perform purchases outside the user’s expected consent boundaries.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · crossmint-wallet.md (reported line 32)May include surrounding context.

Purchase Request

bash
curl -X POST https://creditclaw.com/api/v1/card-wallet/bot/purchase \
  -H "Authorization: Bearer $CREDITCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file expands an Amazon shopping skill into a generic card-enabled purchasing capability for arbitrary merchants. That materially broadens the authority of the agent beyond the declared scope, increasing the chance of misuse, policy bypass, or user confusion about where payment credentials may be used.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · encrypted-card.md (reported line 59)May include surrounding context.

Step 1: Request Checkout

bash
curl -X POST https://creditclaw.com/api/v1/bot/rail5/checkout \
  -H "Authorization: Bearer $CREDITCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The checkout flow explicitly supports purchases at arbitrary merchants, not just Amazon, while using delegated card access. In an agent setting, this creates a dangerous capability expansion: any prompt or workflow that reaches this skill could authorize payment attempts on third-party sites outside the user's expected context.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

The documented auto-approve threshold enables purchases to proceed without per-transaction human review when they fall within configured limits. In an agent ecosystem vulnerable to prompt injection or mistaken intent, autonomous spending is a meaningful financial-risk capability even if bounded by thresholds.

Content

Scanner excerpt · encrypted-card.md (reported line 108)May include surrounding context.

"approved": false, "status": "pending_approval", "checkout_id": "r5chk_abc123", "message": "Amount exceeds auto-approve threshold. Your owner has been notified.", "expires_in_minutes": 15 }

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This endpoint delivers a one-time decryption key for card material to the agent runtime. Sending decryption keys into an LLM-controlled execution environment is dangerous because any prompt injection, logging, tracing, memory capture, or tool misuse in that environment could expose the key and enable card decryption.

Content

Scanner excerpt · encrypted-card.md (reported line 164)May include surrounding context.

The sub-agent calls this endpoint to retrieve the one-time decryption key:

bash
curl -X POST https://creditclaw.com/api/v1/bot/rail5/key \
  -H "Authorization: Bearer $CREDITCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "checkout_id": "r5chk_abc123" }'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the agent to save a self-contained encrypted card file locally without prominent warnings or controls for secure storage, retention, file permissions, or host compromise. Even though the card is encrypted at rest, the file is payment material tied to later key retrieval and decryption, so mishandling on disk increases theft, tampering, and accidental disclosure risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file instructs the user to call remote API endpoints with an Authorization bearer token, which will transmit sensitive wallet, balance, and permissions data to an external service. The description includes no explicit warning about privacy, credential handling, or the fact that these checks disclose account data to CreditClaw.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · management.md (reported line 23)May include surrounding context.

When your balance is low, ask your human if they'd like you to request a top-up:

bash
curl -X POST https://creditclaw.com/api/v1/bot/wallet/topup-request \
  -H "Authorization: Bearer $CREDITCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · skill.md (reported line 35)May include surrounding context.

| package.json (metadata) | https://creditclaw.com/amazon/skill.json | Machine-readable skill metadata | Follow your human's instructions on how to manage and save skill files. If unsure, you can install locally:

bash
mkdir -p ~/.creditclaw/skills/amazon
curl -s https://creditclaw.com/amazon/skill.md > ~/.creditclaw/skills/amazon/SKILL.md
curl -s https://creditclaw.com/amazon/checkout.md > ~/.creditclaw/skills/amazon/CHECKOUT.md
curl -s https://creditclaw.com/amazon/crossmint-wallet.md > ~/.creditclaw/skills/amazon/CROSSMINT-WALLET.md

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · skill.md (reported line 36)May include surrounding context.

Follow your human's instructions on how to manage and save skill files. If unsure, you can install locally:

bash
mkdir -p ~/.creditclaw/skills/amazon
curl -s https://creditclaw.com/amazon/skill.md > ~/.creditclaw/skills/amazon/SKILL.md
curl -s https://creditclaw.com/amazon/checkout.md > ~/.creditclaw/skills/amazon/CHECKOUT.md
curl -s https://creditclaw.com/amazon/crossmint-wallet.md > ~/.creditclaw/skills/amazon/CROSSMINT-WALLET.md
curl -s https://creditclaw.com/amazon/encrypted-card.md > ~/.creditclaw/skills/amazon/ENCRYPTED-CARD.md

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 123)May include surrounding context.

You can register before your human does. You'll get an API key immediately.

bash
curl -X POST https://creditclaw.com/api/v1/bots/register \
  -H "Content-Type: application/json" \
  -d '{
    "bot_name": "my-research-bot",

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
89% confidence
Finding

The skill explicitly permits autonomous spending under certain approval modes and thresholds. Even though guardrails are described as server-side enforced, this still enables the agent to initiate real financial transactions without per-transaction human confirmation, which is a meaningful safety risk if the agent is misdirected, compromised, or operating on flawed inputs.

Content

Scanner excerpt · skill.md (reported line 321)May include surrounding context.

md
**You must follow these rules:**
- If `approval_mode` is `ask_for_everything`, ask your human before any purchase to get their approval. **New accounts default to this mode.** Your owner can loosen this from their dashboard once they're comfortable.
- If `approval_mode` is `auto_approve_under_threshold`, you may spend freely up to `ask_approval_above_usd`. Anything above that requires owner approval.
- If `approval_mode` is `auto_approve_by_category`, you may spend freely on `approved_categories` within limits. All others require approval.
- **Never** spend on `blocked_categories`. These are hard blocks enforced server-side and will be declined.
- Always read and follow the `notes` field — these are your owner's direct instructions.