hexdocs-fetcher

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and extract documentation from the public site hexdocs.pm using WebFetch (e.g., WebFetch(url: "https://hexdocs.pm/oban", ...)), meaning the agent will read and act on untrusted third‑party documentation that can influence its behavior and enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill issues runtime WebFetch calls to fetch HexDocs pages (e.g., https://hexdocs.pm/oban) and injects that fetched content into the agent context per provided prompts, so remote content can directly control the agent's instructions.