framing-doc
Fail
Audited by Snyk on Mar 5, 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 capturing and reproducing verbatim quotes from transcripts (attributed in the output), so if those transcripts contain API keys, tokens, cookies, or passwords the model is explicitly instructed to output them, creating an exfiltration risk.
Audit Metadata