transcript-polisher
Fail
Audited by Snyk on Feb 24, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill mandates preserving exact wording and never removing substantive content, so if a transcript contains API keys, tokens, passwords, or other secrets the LLM would be expected to reproduce them verbatim, creating an exfiltration risk.
Audit Metadata