create-research-questions

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 explicitly fetches and reads GitHub issues via gh issue view <number> --repo <owner/repo> and Linear tickets via CLI/API and then "Read the ticket fully using the Read tool," which means it consumes untrusted, user-generated third-party issue/ticket content that can directly influence the generated research questions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches ticket content at runtime using commands like "gh issue view --repo <owner/repo> --json ..." for GitHub issues (owner/repo#123) and via the Linear CLI/API, which would inject external ticket text into the agent's context and thus directly control the agent's prompts when a GitHub/Linear ticket input is provided.