research-git
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In Mode A/B/C/D the workflow discovers and then fetches outsider-authored repo files (e.g., SKILL.md and references/, .github/workflows/, README/docs/) from shortlisted public GitHub repos via
scripts/search_repos.sh+scripts/fetch_repo_assets.sh, which then feeds fetched free text to LLM prompts for extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata