gpt-5-6-prompt-builder
Fail
Audited by Snyk on Jul 14, 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 explicitly instructs including user-provided prompts "verbatim" for migrations and to output a single copyable GPT-5.6 prompt, which would force any secrets present in the input to be reproduced verbatim in the LLM's output.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata