stream-of-consciousness
Fail
Audited by Snyk on Feb 14, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly exports the entire conversation including tool outputs and optional internal traces and allows invocation with options (e.g., include-internal + internal=full or redact=none) that would force verbatim inclusion of secrets, tokens, or passwords present in the context.
Audit Metadata