anysearch

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

• Third-party content exposure detected (low risk: 0.10). The workflow allows the agent to search the web and extract arbitrary URL content using external search results and selected web pages.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading a ZIP archive from GitHub via curl/wget during setup (README.md), which constitutes an operational remote repository locator used to obtain installed skill material.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The string as_sk_16c4f23c66e3a3b9c9683f79090fa912 found in .env:11 is a high-entropy, literal API key that provides active authentication and access to the AnySearch service. This is a real credential leak in a configuration file.