clawpatch-report-only

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

• Third-party content exposure detected (high risk: 0.70). Outsider-authored free text can enter the LLM context via clawpatch ... review/report/show/revalidate/triage because ClawPatch ingests the target repository’s existing files (e.g., issue/PR/wiki/discussion text or other third-party content) as readable prose at runtime.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime commands invoke remote code via "npx --yes clawpatch@latest" (which fetches and executes the package from the npm registry, e.g. https://registry.npmjs.org/), so external code is retrieved and run at runtime.