memory-intake
Fail
Audited by Snyk on Feb 17, 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 instructs the agent to ingest raw user input and include that content verbatim in previewed nmem_remember calls and stored memories, so any API keys/passwords present in the input would be echoed and persisted by the LLM.
Audit Metadata