session-export
Fail
Audited by Snyk on Feb 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The fallback mode explicitly instructs the AI to write each message from the current conversation context verbatim into the export, which will include any API keys, passwords, or tokens present in the conversation and thus requires the LLM to output secret values.
Audit Metadata