develop-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly resolves and reads a same-repository GitHub issue (see Quick Start/Input Contract: invoking /develop-issue with an issue URL and "Resolve the issue through the current working directory's default gh repository"), which is user-generated content that the agent is expected to interpret and which can materially influence implementation decisions and tool use.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime install commands that fetch and execute remote packages via npx (e.g., "npx skills@latest add patinaproject/skills" and "npx skills@latest add mattpocock/skills@tdd"), so these external repositories would be downloaded and run as required child skills at runtime.