skill-creator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to "read the existing project code" and "Always use real project code as examples" (including "real example code" and minimum examples) which can force the LLM to copy verbatim code from the repo — potentially including API keys, tokens, or other secrets — into generated SKILL.md files.