apm-issue-autopilot
Warn
Audited by Snyk on Aug 22, 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). In
assets/triage-prompt.md(Phase 1), a triage child reads outsider-authored GitHub issue free text (ISSUE_BODY) and linked references in DIRECT mode to produce theautopilot-triage-decisionJSON, so an outsider can poison via issue content the workflow ingests without first selecting a specific item beyond the queue/list.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata