github
Warn
Audited by Snyk on Mar 11, 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.md shows the agent fetching and proxying GitHub content (e.g., list-issues, get-pull-request, search-issues and the general
membrane requestproxy) from public/user-generated GitHub repos and issue/PR text, which the agent is expected to read and which can materially influence follow-up actions like commenting or merging.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata