scaffold-project
Warn
Audited by Snyk on Aug 11, 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 workflow ingests outsider-authored free text at runtime via the WebSocket endpoint (
TriageSocket→TriageBridge.triage(String ticket)) and passes it as{ticket}into entry sub-agents’ LLM prompts (with guardrails), so an outsider can supply arbitrary text to the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata