review
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The workflow’s runtime path explicitly runs
entire explain --checkpoint <checkpoint-id> --jsonandentire session current --json, which ingests checkpoint transcript text and in-progress session prompts authored by others (outsider) into the agent’s LLM context for intent-aware review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata