production-audit

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs npx commitshow@0.3.23 audit ... --json, which calls the public audit engine/API and ingests its returned concerns[].bullet/strengths[] text into the agent’s LLM context—an outsider-authored free-text source (public web/API output) that can carry indirect prompt-injection content.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill runs the external CLI via "npx commitshow@0.3.23" which downloads and executes remote npm package code and calls the public API (e.g. https://api.commit.show/audit?repo=...&format=json), and the returned JSON (concerns[].bullet) directly controls agent output, so this is a runtime external dependency that executes remote code and drives prompts.