pypi

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

• Third-party content exposure detected (low risk: 0.10). The skill searches PyPI (pypi.org), a public package repository where third parties can publish packages containing arbitrary text that the agent ingests upon searching.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill configures and connects an external Model Context Protocol (MCP) server hosted at https://unbrowse.ai/mcp/pypi.org, relying on it for runtime tool execution and instructions under third-party Unbrowse provenance, creating a high-risk operational dependency.