hns-lsel-curator
Warn
Audited by Snyk on Aug 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). In the PROPOSE/M2 flow, the agent reads prior topic files from
~/.claude/projects/<hash>/memory/via retrieval-before-propose and thosefeedback_*.mdfiles are user-authored content that can contain arbitrary free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata