ad-conf-check

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires parsing user-provided YAML configs and "ALWAYS" outputting one row per config with the config key and its value (and writing those values to JSON/table outputs), so any secrets present in those configs would be included verbatim in the LLM's output, creating an exfiltration risk.