library-docs
Warn
Audited by Snyk on Feb 16, 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 explicitly clones and explores public repositories (e.g., "git clone https://github.com/{owner}/{repo}.git" into /tmp/cc-repos and by searching GitHub, PyPI, crates.io) and directs a research agent to read READMEs and source code, which exposes the agent to untrusted, user-generated third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill performs a runtime git clone from URLs like https://github.com/{owner}/{repo}.git and then launches a Research subagent to explore that repository and use its files to form answers, which injects external repository content into the agent's prompt/context at runtime (https://github.com/{owner}/{repo}.git).
Audit Metadata