make-explainer

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads the local project's code and docs, but step 2 instructs the agent to read pull requests ("Read the project's code, docs and pull requests"), which exposes it to outsider-authored free text from GitHub PRs.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an unofficial third-party GitHub repository (yahyabedirhan/explainer-studio) as the source for the explainer studio software which is cloned and set up at runtime, resulting in a medium-tier unofficial operational dependency.