handoff
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow writes a handoff markdown file summarizing the current conversation, which necessarily includes the conversation text (potentially containing outsider-authored free-form messages) into the agent’s LLM context via the handoff content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata