github-operations
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly clones and pulls arbitrary GitHub repositories (e.g., clone_repo capability and the "git clone https://github.com/user/ai-skills.git" / "Install skills from a GitHub repo" examples in SKILL.md and schema), meaning it ingests user-generated, public GitHub content that the agent is expected to read/interpret as part of workflows and which could materially influence subsequent git/API actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata