create-rule
Warn
Audited by Snyk on Jun 17, 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 user-provided free-form text via
AskUserQuestionprompts (e.g., Title/Description/Rationale/OCIL/CCE/reference fields) into the agent’s LLM context, which is outsider-authored relative to the operating user’s chosen inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata