extract-transcripts
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 extracts and emits raw session content (including tool calls with --include-tools) from local JSONL files verbatim, so any API keys, tokens, cookies, or passwords present in those sessions would be reproduced in the output.
Audit Metadata