leave-task
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and read task data from the OpenAnt service (e.g., "npx @openant-ai/cli@latest tasks get --json" and "Show the task title and reward"), which is user-generated third-party content the agent must interpret and that can materially influence whether to unassign the task.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill instructs running the runtime command "npx @openant-ai/cli@latest", which fetches and executes remote npm package code at runtime (a required dependency for unassigning), so this is a runtime external dependency that can execute remote code.
Audit Metadata