recall

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill tells the agent to read and "show Joel what you found" from files, session transcripts, Vault and Redis (via cat/grep/session_context/redis-cli) with no guidance to redact secrets, so any API keys/passwords present in those sources could be output verbatim.