active-interleave
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill reads and emits fragments from local message/session stores (~/.../messages, cognition.duckdb) and instructs the agent to "emit interleaved fragments" verbatim, so any secrets contained in those messages could be output and exfiltrated.
Audit Metadata