client-revisions
Warn
Audited by Snyk on Jun 23, 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 is triggered by “A note arrives” from the client/stakeholders; those notes are free-form outsider-authored text (e.g., messages/comments/emails) that the agent must read and classify, so it can be fed into the LLM context for decisioning/translation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata