github-issues
Warn
Audited by Snyk on Mar 2, 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 falls back to fetching and parsing public GitHub issue pages (via WebSearch, firecrawl MCP scraping, direct WebFetch URLs, and the GitHub API) and instructs the agent to read issue bodies/comments to drive searches, troubleshooting, and follow-up actions, exposing it to untrusted user-generated content from github.com.
Audit Metadata