dbs-goal
Fail
Audited by Snyk on Jul 27, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). In Phase 1 and the output template the skill requires the agent to record and verbatim-embed the user's "原话"/逐字引用, so if a user submits API keys/passwords/cookies the LLM would be forced to reproduce them in its output.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata