command-creation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly supports injecting shell output (!command) and file contents (@path) directly into prompts sent to the LLM, which can cause secrets (env vars, .env files, tokens from CLI output) to be read and echoed verbatim, creating an exfiltration risk.