apm-issue-autopilot
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the Phase 1 triage children: the orchestrator passes
ISSUE_BODY(verbatim from GitHub issues authored by non-operators) intoassets/triage-prompt.md, which the triage child then reads and uses in DIRECT mode withapm-triage-panel.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata