piu-frontend-sync

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly clones an arbitrary frontend repository with "git clone " (Step 1) and scans its code for HTTP call patterns to drive matching, reporting, and optional auto-fix actions (create-request/create-model), so untrusted, user-generated repo content is ingested and can materially change the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs git clone --depth 1 at runtime to fetch a remote frontend repository and then parses that repository's files to drive its analysis/reporting (i.e., injecting fetched code/metadata into the agent's runtime context), so the external repo URL () can directly influence agent behavior.