comment-on-task

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md instructs the agent to run "npx @openant-ai/cli@latest tasks comments --json" to read task discussion items (user-generated "content") that the agent is expected to interpret as part of its workflow and could influence its actions, 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: 0.90). The skill runs "npx @openant-ai/cli@latest" at runtime, which fetches and executes remote package code from the npm registry, so it relies on executing external code fetched at runtime.