researcher
Warn
Audited by Snyk on Aug 26, 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). The skill’s documented workflow describes performing GitHub code search and “extracting patterns” from top repositories, which implies the LLM will ingest outsider-authored free text from GitHub issue/PR/code content when conducting the research.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata