triaging-issues
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). This skill reads and processes user-generated GitHub issue content via mcp__github__issue_read (including issue bodies, comments, and external links such as Google Drive, Dropbox, and Hugging Face links referenced in Step 1.5), exposing the agent to untrusted third-party content that could carry indirect prompt injection.
Audit Metadata