ClawHub
Back to skill

Security audit

Clawpay

Security checks for vulnerabilities and agentic risk

Overview

This payment skill is mostly coherent, but it needs review because it can create crypto payment flows while using an unsafe default recipient and under-disclosing third-party data handling.

Review before installing. Use only with explicit user approval for each payment request, verify the final recipient wallet address, network, asset, amount, and counterparty, do not rely on the packaged zero-address default, and avoid sending secrets or sensitive personal data in delivery payloads. Prefer an install source with pinned versions and checksum or signature verification.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:25
Finding

Unverified Remote Skill Installation Enables Supply-Chain Modification

Content
View full analysis
~/.openclaw/skills/clawpay/SKILL.md curl -s https://clawpay.ai/heartbeat.md > ~/.openclaw/skills/clawpay/HEARTBEAT.md curl -s https://clawpay.ai/skill.json > ~/.openclaw/skills/clawpay/package.json ``` ``` ### Technical Analysis The documented installation procedure downloads mutable files from `clawpay.ai` directly into the active local skill directory. It does not pin an immutable artifact version or verify a cryptographic signature, checksum, or trusted release manifest. HTTPS protects the connection in transit when certificate validation operates correctly, but it does not ensure that the server continues to provide the same content that was reviewed. If the hosting account, deployment pipeline, origin server, or domain is compromised, the downloaded `SKILL.md` and `HEARTBEAT.md` could contain altered agent instructions. The installation commands would overwrite local files without displaying or validating their contents. The use of `curl -s` without `--fail` also suppresses normal progress and error output and can write an HTTP error response into an expected skill file. No evidence shows that the currently audited remote content is malicious. The risk arises from the installation mechanism trusting mutable external artifacts without integrity verification. ### Attack Path 1. An attacker compromises the `clawpay.ai` origin, deployment pipeline, hosting account, or another mechanism controlling the referenced resources. 2. The attacker replaces `skill.md`, `heartbeat.md`, or `skill.json` with modified content. 3. A user follows the documented installation procedure. 4. `curl` writes the attacker-controlled artifacts directly into `~/.openc ...[truncated 803 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
package.json:5
Finding

Zero Address Configured as the Default Cryptocurrency Payment Recipient

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

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 · HEARTBEAT.md (reported line 7)May include surrounding context.

List pending requests

bash
curl "https://clawpay.ai/v1/requests?status=pending"

Pick any request_id you are tracking. Then:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill says to use it for 'any agent-to-agent or human-to-agent exchange,' which is overly broad and lacks trigger constraints, approval gates, or limitations on when payment collection should occur. In an agent setting, this can cause inappropriate invocation for arbitrary tasks and can normalize sending users into a payment flow without sufficient context, validation, or policy checks.

Content

No source excerpt is available for this finding.

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 26)May include surrounding context.

Install locally:

bash
mkdir -p ~/.openclaw/skills/clawpay
curl -s https://clawpay.ai/skill.md > ~/.openclaw/skills/clawpay/SKILL.md
curl -s https://clawpay.ai/heartbeat.md > ~/.openclaw/skills/clawpay/HEARTBEAT.md
curl -s https://clawpay.ai/skill.json > ~/.openclaw/skills/clawpay/package.json

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 27)May include surrounding context.

Install locally:

bash
mkdir -p ~/.openclaw/skills/clawpay
curl -s https://clawpay.ai/skill.md > ~/.openclaw/skills/clawpay/SKILL.md
curl -s https://clawpay.ai/heartbeat.md > ~/.openclaw/skills/clawpay/HEARTBEAT.md
curl -s https://clawpay.ai/skill.json > ~/.openclaw/skills/clawpay/package.json

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 27)May include surrounding context.

Install locally:

bash
mkdir -p ~/.openclaw/skills/clawpay
curl -s https://clawpay.ai/skill.md > ~/.openclaw/skills/clawpay/SKILL.md
curl -s https://clawpay.ai/heartbeat.md > ~/.openclaw/skills/clawpay/HEARTBEAT.md
curl -s https://clawpay.ai/skill.json > ~/.openclaw/skills/clawpay/package.json

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions direct the agent/operator to send request metadata, payment details, and optional delivery payloads to clawpay.ai, but they do not warn that this information is transmitted to a third-party service. This creates a meaningful privacy and data-handling risk, especially because the deliver endpoint may contain arbitrary payload data that could include sensitive content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.