validate-v2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires validators to read repository files and emit "code snippet" evidence and exact Forward-Compatibility/Thesis blocks verbatim, so any hard-coded secrets (API keys, tokens, .env values, cookies) present in those files would be copied verbatim into the LLM output, creating an exfiltration risk.

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

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