accept-task
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's "Check the Task First" workflow explicitly tells the agent to run "npx @openant-ai/cli@latest tasks get --json" to fetch task details (including the user-generated "description") from the OpenAnt platform, which the agent must read and act on when deciding to accept or apply, exposing it to untrusted third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill requires running remote code via the npx command "npx @openant-ai/cli@latest" at runtime, which fetches and executes code from the npm registry and therefore is a runtime external dependency that can execute remote code.
Audit Metadata