agent-style
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a comprehensive set of writing rules based on established linguistic authorities such as Strunk & White, Orwell, and Pinker. The content is purely educational and instructional.
- [SAFE]: References to external resources, such as the
agent-styleCLI and its GitHub repository, are provided for documentation and optional auditing purposes. These align with the skill's stated goal of improving writing quality and do not involve automated execution of untrusted code. - [SAFE]: No malicious patterns, such as prompt injection, unauthorized data access, or obfuscation, were identified in the provided files.
- [SAFE]: The skill processes user-provided prose to perform style revisions. While this constitutes an attack surface for indirect prompt injection, the skill does not have exploitable capabilities like network exfiltration or arbitrary command execution that would be triggered by the input.
Audit Metadata