writing-prompts
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The content of the skill is purely documentation. It provides a framework for prompt engineering, including role definition, task specification, and output formatting.
- [PROMPT_INJECTION]: Static analysis identified keywords such as "ignore previous instructions." However, these terms appear exclusively within the context of teaching users how to build defense layers and write injection-resistant prompts. The skill does not attempt to override the current agent's instructions.
- [DATA_EXFILTRATION]: There are no network requests, API calls, or commands that interact with the file system or environment variables.
- [REMOTE_CODE_EXECUTION]: The skill does not include any scripts, package dependencies, or commands for remote code execution.
Audit Metadata