agent-watchdog

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads PRs, issues, commits, and review comments from external repositories and platforms, which exposes the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The install command in README.md references an external npm package URL/locator (@agent-native/skills) used to download and install skill material, constituting a common unofficial operational dependency.