resolve-pr-feedback
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill fetches and ingests user-generated PR review threads and comment bodies from GitHub (see scripts/get-pr-comments and SKILL.md step 4, which passes "the full comment text" to spawned agents) and uses that untrusted content to drive code changes, replies, and agent decisions, creating a clear avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata