professional-proofreader
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a standard utility for text correction. Its workflow is transparently described and limited to proofreading tasks, voice preservation, and saving updated document versions.
- [PROMPT_INJECTION]: The skill processes external text and files, representing an indirect prompt injection surface. This is evaluated as safe given the lack of exploitable capabilities and the alignment with the skill's primary purpose.
- Ingestion points: The skill reads inline text pasted by the user and the full contents of uploaded document files (.docx, .pdf, .txt).
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore commands within the source text.
- Capability inventory: Capabilities are restricted to reading file contents and writing new files to the local file system.
- Sanitization: Absent; the skill is designed to process and return the author's original text with minimal edits.
Audit Metadata