fetching-github-issue
Warn
Audited by Snyk on May 8, 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). This skill explicitly reads GitHub issue bodies and comments via the GitHub read path (see ./subagents/issue-retriever.md and SKILL.md: use of
gh issue viewandgh api .../comments/timeline), ingesting untrusted, user-generated content and using that content to extract Acceptance Criteria, populate the snapshot, and drive downstream workflow decisions—allowing third-party text to materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata