whoami

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to capture arbitrary "candidate" claim text from scans and then embed that text verbatim into shell command arguments (--claim "$CANDIDATE") and into synthesized JSON outputs, so any secrets discovered in the scan would be included directly in commands/files and the LLM output, creating an exfiltration risk.