file-search
Warn
Audited by Snyk on May 6, 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). The skill's SKILL.md "Beyond Local Files" section and the included references/remote-handoff.md explicitly instruct handing off to remote tools (gh, Jira, WebFetch, Playwright) to fetch issues/PRs, wikis, and web docs — untrusted, user-generated third‑party content the agent is expected to read and which can materially influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata