piu-backend-sync

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples and CLI commands (e.g., set-vars with {"key":"token","value":"your-auth-token"} and request bodies showing plaintext passwords/tokens) instruct placing secrets directly into JSON/command arguments, which would require the LLM to emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly clones arbitrary repositories ("git clone --depth 1 " in Step 1) and reads router and controller source files (Step 2 and Step 4) from those untrusted third‑party codebases to extract routes/models that directly drive creation of PIU entities and subsequent actions, so external content could influence agent behavior.