build-skill

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads and searches external GitHub repositories and registries via scripts like skill-dl.mjs and run-research, but these are initiated via explicit user-authored queries rather than an unauthenticated monitored feed of outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The instruction in SKILL.md requires installing and using the remote companion skill skills/run-research via GitHub and npx from yigitkonur's personal repository without authentication or integrity enforcement, which is an external operational dependency with weak provenance.