ClawHub
Back to skill

Security audit

Atoship

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only shipping skill is coherent and disclosed, though users should treat its API key as payment-capable.

Install only if you are comfortable giving your assistant access to an atoship API key that can buy and void shipping labels. Start with a sandbox key or small wallet balance, keep spending alerts enabled, and require explicit confirmation for purchases, voids, and preferably order creation too.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

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 170)May include surrounding context.

Example: Track a package

bash
curl -X GET "https://atoship.com/api/v1/tracking/9400111899223456789012" \
  -H "Authorization: Bearer ak_live_your_key_here"

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 241)May include surrounding context.

md
> **Rule for AI assistants**: You MUST ask the user for explicit confirmation before calling `purchase_label` or `void_label`. Display the action summary (carrier, service, price, addresses) and wait for a "yes" or "confirm" response. Never execute wallet-affecting actions autonomously.

**Read-only actions (safe to call without confirmation):**
- `get_shipping_rates`, `track_package`, `list_labels`, `get_label`, `get_account`, `list_carrier_accounts`, `validate_address`, `list_orders`, `get_order`, `create_order`

**Recommendations:**

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
Go to Dashboard → Billing to add postage credit. Labels are deducted from your wallet balance — you only pay for what you ship.

> **Note on permissions:** Your API key authorizes label purchases and wallet charges. We recommend:
> - Start with a small wallet balance (e.g. $20) while evaluating
> - Use a test/sandbox key (`ak_test_...`) for development — test labels are free and never shipped
> - Set spending alerts in Dashboard → Billing → Notifications

Static analysis

No suspicious patterns detected.