create-pr
Warn
Audited by Snyk on Feb 25, 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's "Auto PR Linking" note in SKILL.md states that sessions can be resumed with --from-pr and that "PR context (diff, comments, review status) is available when resuming," which means the agent will fetch and interpret user-generated GitHub PR content (comments/reviews) that could influence its actions.
Audit Metadata