distill-session
Fail
Audited by Snyk on Mar 30, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill explicitly requires pasting verbatim prompts and full model outputs into saved files (and re-emitting them during extraction), so if those contain API keys, tokens, or passwords the agent must handle and output them exactly, creating a high exfiltration risk.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata