security-reviewer

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches package metadata from the public npm registry via curl during the package-guard hook execution, exposing the agent to outsider-authored package metadata.

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

• Potentially malicious external URL detected (high risk: 0.70). The hook script fetches package metadata from the npm registry via curl at runtime to perform freshness checks, presenting a weak/unknown provenance risk tier.