my-knowledge
Warn
Audited by Snyk on Aug 25, 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 SKILL.md, the required workflow for
/my-knowledgeexplicitly requires reading the full conversation history at invocation time (including outsider-authored user messages) and then scanning those messages for topics and signals, which exposes the agent to user-provided free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata