issue-branch-pr-flow

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow directs the agent to read and follow the instructions in the github skill, which involves reading GitHub issues and pull requests containing outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches external instructions and command-line tooling from an arbitrary personal GitHub repository (philtzjp/skills), constituting a weak/unknown operational dependency.