code-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Documentation Discovery" explicitly fetches and ingests public URLs (e.g., curl to https://docs.pydantic.dev/llms.txt, checking .well-known/agentskills.io, and a generic "fetch" tool for any URL), so the agent is expected to read arbitrary third-party web content that could be untrusted.