factor-blend
Warn
Audited by Snyk on Aug 12, 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). SKILL.md / agents/openai.yaml define an LLM prompt template that directly includes the runtime field “task” (“{{task}}”)—user-supplied free text—into the agent’s prompt before any factor-selection step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata