reflect
Warn
Audited by Snyk on Nov 13, 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 workflow reads the user's own session history (ccrecall.db or the in-context window), which can include tool output from web pages or other arbitrary content the agent fetched earlier, but an outsider cannot force that content into the workflow without the agent first retrieving it.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata