task-system
Warn
Audited by Snyk on Jun 20, 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). Outsider free-form text can be ingested from
.agents/tasks/inbox.mdvia the runtime pathtasks inbox(inbox.md is explicitly “Anyone, any time” free-form), and that content is then used to draft tasks and potentially inserted into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata