fix-github-issue

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

• Third-party content exposure detected (high risk: 0.95). The workflow explicitly fetches GitHub issue body text authored by an outsider (the issue author/other contributors) via gh issue view ... --json title,body,labels,state, which is then parsed/used by the agent at runtime.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches live GitHub issue content at runtime via the gh CLI (e.g., "gh issue view <owner/repo>#"), and the remote issue body is used to directly determine the agent's implementation instructions, so this is a runtime external dependency that controls prompts.