lakehouse-table-inspection
Fail
Audited by Snyk on Aug 2, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill includes an inline credential placeholder ("credential": "oauth2_token...") and instructs the agent to prompt or connect to catalogs, which could lead the LLM to request and embed user API tokens/credentials verbatim (exfiltration risk).
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata