support-engineer
Warn
Audited by Snyk on Jun 13, 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). The skill’s runtime workflow ingests customer-provided bug reports (e.g., “Error message verbatim; request/correlation ID” and “Follow customer steps… Capture HAR, server logs…”) which are outsider-authored free text from the customer into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata