supabase-evidence

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires collecting full HTTP requests and curl commands (including Authorization/apikey headers) and even shows examples/variables where an actual anon/service key would be inserted, which would force the LLM to handle or output secret values verbatim unless strict redaction is applied.

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

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