chat-history
Fail
Audited by Snyk on Feb 15, 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 extracting and writing "actual user input text" from local Claude session files verbatim into .chats files (and committing them), which will include any API keys, tokens, or passwords a user typed and therefore requires the LLM/agent to output secret values verbatim.
Audit Metadata