humanize-ai-text
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill consists of instructional text for the AI agent and does not utilize any scripts, subprocesses, or file system operations.
- [EXTERNAL_DOWNLOADS]: The skill mentions the author's NPM package (
@rephrasy/mcp) and website (rephrasy.ai) in a documentation footer. These resources are identified as legitimate vendor tools and do not involve silent or unverified downloads. - [PROMPT_INJECTION]: The instructions are strictly focused on text humanization and stylistic changes. There are no attempts to override agent behavior, bypass safety protocols, or extract system instructions.
- [DATA_EXPOSURE]: The skill does not access sensitive file paths, environment variables, or hardcoded credentials.
Audit Metadata