mirror-reference
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md:13-16 directs the agent to “study each reference” by fetching external resources (URLs/docs via web fetch or other repos via
gh/API) and then read/identify the pattern from that fetched content, which would be outsider-authored free text ingested into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata