resolve-merge-conflicts

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow instructs the agent to read GitHub pull request/issue information via gh pr view to understand conflicting changes, which can contain 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 an external SKILL.md file from a personal GitHub repository at runtime when a sibling copy is missing, constituting an unverified third-party operational dependency.