security-auditor

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

• Third-party content exposure detected (high risk: 0.70). The skill's dependency scanning and optional network configuration explicitly allow fetching package metadata/vulnerability data from public registries and APIs (registry.npmjs.org, pypi.org, api.github.com), which are untrusted, user-contributed third-party sources the agent would read and interpret as part of its workflow.