changesets
Warn
Audited by Snyk on Apr 20, 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 explicitly reads PR title and body via
gh pr view --json title,body(step 5 in SKILL.md) and uses those user-generated PR contents to decide bump type and whether to write or modify changesets, so external/untrusted PR text can materially influence its decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata