kata-plan
Warn
Audited by Snyk on Nov 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required grounding stage can fetch external web documentation for versioned dependencies, which is an agent-selected lookup of content that may be outsider-authored, so exposure requires the agent to actively search or fetch it rather than receiving submitted text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata