component-writeup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires embedding "realistic examples from the target's actual artifacts (code, config, schema)" and anchoring claims to file contents without any instruction to redact or avoid sensitive fields, so the LLM may need to extract and output secrets (API keys, tokens, passwords) verbatim from configs or code snippets.