public-release

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.95). The prompt requires an exhaustive secrets-and-git-history audit and asks for precise findings (file:line, "Secrets ever committed", problematic commits, and examples/commands to remove specific strings), which implies the LLM would need to surface secret values or exact secret-containing snippets verbatim — a high exfiltration risk.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)