llm-golden-dataset-builder
Fail
Audited by Snyk on Apr 23, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill directs the agent to read production logs/traces and present/save raw "input" and "output" fields verbatim into the golden dataset, which can contain API keys, tokens, cookies, or passwords — forcing the LLM to handle and output secret values directly.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata