audit-onboarding-proposal
Warn
Audited by Snyk on Jul 29, 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 the Evidence-capsule route, the runtime reads an outsider-authored transcript file/its last assistant message from a raw-session.jsonl path (and potentially machine tool output) and parses free text (including JSON capsule, patch diffs, and claim lines) to extract and validate evidence.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata