conventions
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-only artifact providing guidelines for naming conventions, directory structures, and prompt engineering layers. It contains no executable scripts or commands.
- [CREDENTIALS_UNSAFE]: The reference to
OPENAI_API_KEYis used as a placeholder example in a table explaining naming conventions (SCREAMING_SNAKE) and does not represent a leaked secret. - [EXTERNAL_DOWNLOADS]: External links to documentation sites (agentskills.io) and reference repositories (github.com/karpathy/autoresearch) are provided for context and do not involve automated downloading or execution of code.
- [PROMPT_INJECTION]: Instructions regarding "Positive framing" and "Role/persona" are standard prompt engineering techniques used to improve model performance and do not attempt to bypass safety guardrails.
Audit Metadata