search-tasks

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md instructs the agent to run the OpenAnt CLI (e.g., npx @openant-ai/cli tasks list and tasks get) to fetch task listings and task "description" fields from the OpenAnt platform — user-created, public content that the agent is expected to parse and use to decide next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill requires running "npx @openant-ai/cli@latest" at runtime, which fetches and executes remote package code from the npm registry (npx/@openant-ai/cli) as a required dependency, so this external fetch executes remote code.