treebuy-search

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries the public treebuy API (GET https://v2api.treebuy.com/v2/product/search) as shown in SKILL.md and references/api.md and consumes product fields (name, subtitle, special_title, etc.) that the agent is expected to read and use (e.g., choosing SKUs for follow-up actions), exposing it to untrusted third‑party content that could influence decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's install/run instructions invoke npx/npm to fetch and execute remote code (e.g., https://github.com/nandemo-agent/treebuy-cli and the npm package @nandemo-agent/treebuy-cli@0.1.0), which would run externally retrieved code at runtime and is presented as a required dependency for the skill.