image-to-excel

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt instructs the agent to embed the extracted JSON data verbatim into a shell command (python3 scripts/gen_excel.py '<json_data>'), which would force the LLM to output any sensitive values present in the extracted table (passwords, API keys, tokens) and thus creates an exfiltration risk.