history-insight
Fail
Audited by Snyk on Mar 4, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). This skill instructs the agent to read and extract raw conversation messages from local session JSONL files and feed them into summary/processing tasks without any redaction or secret-handling safeguards, so any API keys/passwords present in sessions could be output verbatim.
Audit Metadata