The Agent Skills Directory

[SAFE]: The skill instructions and associated reference files (Strunk's 'The Elements of Style' and Wikipedia's 'Signs of AI Writing') are purely informational and educational. They provide high-quality guidance for a writing editor agent.
[SAFE]: No instances of prompt injection, data exfiltration, or credential harvesting were detected. The skill does not access sensitive system paths or environment variables.
[SAFE]: No obfuscation techniques, such as Base64 encoding of commands, zero-width characters, or homoglyph attacks, were identified in any of the skill files.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface as it is designed to process and improve untrusted text provided by users. While this surface exists, the risk is mitigated by the skill's specific purpose of identifying and removing AI-generated patterns and artifacts.
Ingestion points: User-supplied text provided to the agent for editing (SKILL.md).
Boundary markers: None explicitly defined in the instructions.
Capability inventory: File reading, writing, and editing tools (SKILL.md frontmatter).
Sanitization: Not present, as the agent is intended to interact directly with the provided text to refine its quality.

writing-quality