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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 6, 2026, 05:51 AM
Issues
1