continuous-learning-v2
Warn
Audited by Snyk on Oct 14, 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). The observer background loop reads session observations from
observations.jsonlcontaining unvalidated tool inputs and outputs and passes them directly to an automated Claude analysis process.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata