transcript-notes
Fail
Audited by Snyk on Apr 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt requires verbatim reproduction of transcript content (quotes, speaker wording, and verification that quotes are verbatim), so if a transcript contains API keys, tokens, or passwords the model would be instructed to output them exactly, enabling secret exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata