do-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses user-generated issue content from git platforms (see modules/issue-discovery.md which calls "gh issue view ... --json title,body,labels,assignees,comments" and glab issue view) and uses those issue bodies/comments to generate task prompts and subagent instructions, so untrusted third‑party issue text can materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill accepts and at runtime fetches issue pages such as https://github.com/owner/repo/issues/42 and https://gitlab.com/owner/repo/-/issues/42 (via gh/glab) and then uses the fetched issue body to generate agent prompts/tasks, so external content directly controls agent instructions.