write-like-jess
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and configuration metadata. It does not include any scripts, commands, or tool invocations that could pose a security risk.
- [SAFE]: The 'Nonnegotiable boundaries' section provides safety-enhancing constraints, such as prohibiting the invention of personal history or the use of private source material.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or network exfiltration patterns were detected. The skill operates purely on the text provided in the prompt context.
- [INDIRECT_PROMPT_INJECTION]: While the skill is intended to process user-supplied text for rewriting, it lacks any dangerous capabilities (e.g., file system access, network tools, or shell execution) that could be abused via indirect injection. The instructions also explicitly command the agent to preserve the original intent and facts of the source material.
Audit Metadata