hunt-grpc

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

• Third-party content exposure detected (medium risk: 0.30). The workflow includes searching code repositories via GitHub CLI (gh search code), which exposes the agent to outsider-authored free text from repositories/PRs/issues.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an arbitrary third-party personal GitHub repository (https://github.com/secengjeff/rapidresetclient) at runtime and building it with Go, representing an unverified operational dependency from a weak provenance source.