scripts
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational, providing guidance on how to define and use scripts in a
composer.jsonfile. It does not contain executable code, remote downloads, or instructions that attempt to bypass safety guidelines. - [DATA_EXPOSURE]: The skill explicitly warns against the anti-pattern of hardcoding secrets in scripts, recommending the use of environment variables instead.
- [PROMPT_INJECTION]: No attempts to override agent behavior or extract system prompts were found. The instructions are standard technical documentation.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download and execution of remote scripts (e.g., curl|bash).
Audit Metadata