arize-compliance-audit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires quoting exact code snippets and file paths in its mandatory "gap detail" output (including findings like hardcoded api_key/secret/token literals), which would force the LLM to reproduce secret values verbatim despite other guidance not to embed credentials — 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)