respond-to-pr-comments-in-blocklist
Warn
Audited by Snyk on Jun 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow fetches PR comments (via the built-in
/pr-commentsor GitHub CLI) and then ingests the comment bodies into the agent context for per-comment processing; those PR comments are authored by outsiders (reviewers/other contributors), creating an indirect prompt-injection exposure path through “comment body” text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata