tech-advisor

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

• Third-party content exposure detected (low risk: 0.10). The agent skill instructs the LLM to perform web searches and fetch arbitrary web pages using tools like web_fetch, web_forager, and Jina Reader, which ingest outsider-authored free text from external sites.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs running uvx and curl commands to fetch external web pages via third-party services like Jina Reader (r.jina.ai), which constitutes an unverified runtime external dependency from an unofficial source with medium tier provenance.