agent-integration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to provide a "LIVE_COMMAND" and then reuses parameters (including that command) to generate files/scripts (e.g., AGENT.md and a test script), which would require the LLM to include any secrets present in that command verbatim in its outputs.