apply-ai-coding-guideline

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

• Third-party content exposure detected (medium risk: 0.30). The workflow clones and reads a third-party guideline repository from GitHub (Step 1: git clone / git fetch and Step 2: opening PORTAL.md and guidelines/{en,zh,ja}), so outsider-authored free text from that repo can be ingested at runtime.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill fetches and uses an external guideline repository at runtime (git clone https://github.com/fang2hou/ai-coding-guideline) which directly controls the agent's instructions and is required for operation.