clean-stop
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The clean-stop workflow ingests the session’s repo/worktree state (e.g., uncommitted diffs/pasted terminal output) and then writes that content into GitHub PR/issue bodies as outbound breadcrumbs, so outsider-authored text is read via repository content created/submitted by the user/third party and can be included without a prior specific-item selection step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata