component-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's mandatory "Deep Research Phase" explicitly requires WebFetch of template YML files from public GitLab URLs (https://gitlab.com/{project}/-/raw/{version}/{file}) and WebSearch of external tool documentation, so the agent will read and act on untrusted third‑party web content that can influence decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires runtime WebFetch of template files from URLs like https://gitlab.com/{project}/-/raw/{version}/{file}, and those fetched YML files are a mandatory input used to drive the agent's analysis/decisions (i.e., they directly control the agent's instructions), so this is a runtime external dependency.