writing-clearly-and-concisely
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional Markdown files for improving writing style. No malicious code, prompt injection, or suspicious data handling was found in any of the seven files. All external links target well-known services like Wikipedia and Project Gutenberg, which are considered safe according to the established trust scope.
- [NO_CODE]: The skill does not include any scripts (Python, Node.js, etc.) or executables. Its functionality is strictly limited to providing textual instructions and reference examples for the agent to follow during text generation.
- [PROMPT_INJECTION]: While the skill involves processing user-provided drafts, it lacks the dangerous capabilities required for an exploit. There are no subprocess calls, network operations, or file system write permissions.
- Ingestion points: User-provided prose drafts are processed via the instruction to 'copyedit and return the revision'.
- Boundary markers: The instructions do not specify any markers to separate user input from system prompts.
- Capability inventory: No dangerous tools or commands are available to the skill.
- Sanitization: Not applicable as no code is executed.
Audit Metadata