The Agent Skills Directory

[SAFE]: The skill's behavior is consistent with its stated purpose as a writing tool. No malicious patterns, obfuscation, or remote code execution were identified.
[SAFE]: File system operations are limited to reading and writing author profiles in the local references/ directory. The instructions include a normalization step (hyphen-case) that prevents path traversal attacks.
[SAFE]: No prompt injection or safety bypass attempts were found. The workflow for iterative style adjustment is standard for a writing assistant and does not target system instructions.
[SAFE]: The skill ingests user-provided text to apply or learn writing styles. This surface for indirect prompt injection is inherent to the skill's purpose and is managed by the underlying model's guardrails.

bilingual-author-style-writer