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
Risk Level
HIGH
Analyzed
Mar 5, 2026, 12:26 AM