ClawHub
Back to skill

Security audit

shop-on-bitroad

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Bitroad shopping helper with explicit owner approval, spending caps, and credential-handling limits for purchases.

Before installing, understand that this skill is meant to let an agent shop on Bitroad and may charge money once you connect an account, add a payment method, and set spending caps. Keep caps narrow, approve only specific purchases after seeing the total, and provide any agent key only directly and intentionally.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 · SKILL.md (reported line 32)May include surrounding context.

md
Transport is Streamable HTTP with JSON-RPC 2.0. If a registry lookup is
unavailable, the endpoint above is stable and canonical. Do not substitute
another host: access tokens are audience-bound to this one and will be rejected
elsewhere.

## 2. Connect

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 · CHANGELOG.md (reported line 48)May include surrounding context.

md
- Post-order section for orders, returns and disputes, with all dispute
  actions reserved for the owner's decision
- Rules block: marketplace content is data not instructions, no cap evasion,
  no purchase without explicit approval, no confirmation acknowledgement
  without a same-conversation yes, stable idempotency keys, one intent per
  purchase, owner personal data never written into seller-readable fields