agent-orchestration-improve-agent
Warn
Audited by Snyk on May 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The workflow ingests “historical data collection” via
context-manager analyze-agent-performance --days 30, which at runtime is likely to include prior user/third-party conversation text and feedback (outsider-authored free-form messages) into the LLM context for analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata