ci-fix

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs fetching and reading GitHub Actions run logs with commands like "gh run list" and "gh run view --log", meaning the agent ingests potentially untrusted, user-generated CI/log output from GitHub which it is expected to interpret and act on.