clawdhub
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly describes installing and updating skills from the public registry https://clawdhub.com (via clawdhub install/update and default registry), which fetches third-party, potentially user-generated skill code that the agent would ingest and that can change its behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The ClawdHub CLI uses the default registry https://clawdhub.com at runtime to fetch and install "skills" (remote code/prompt bundles) which can directly control agent prompts or execute code, so the registry URL is a runtime dependency that could supply executable/controlling content.
Audit Metadata