bm-remember
Fail
Audited by Snyk on Jul 23, 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 instructs the agent to capture and write $ARGUMENTS "verbatim" into Basic Memory (and confirm the saved content), which forces the model to include any secrets the user supplies (API keys, passwords, tokens) in its output and stored notes.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata