skill-management
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: 0.90). The "Dynamic Context Injection" section shows shell commands run before content is sent to Claude (e.g., ❗️
gh pr view --comments), which can pull user-generated, public content (GitHub PRs/comments) into the agent's input and thus expose it to untrusted third-party content.
Audit Metadata