spec
Warn
Audited by Snyk on Apr 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-generated content: SKILL.md and steps/step-01-discover.md allow -f with a URL or GitHub issue and call
gh issue view, and they launch "general-purpose" subagents for web research, so untrusted/public web content (GitHub issues, arbitrary URLs, search results) is read and used to drive spec decisions and downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata