humanizer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to perform text rewriting tasks. Because the instructions do not specify the use of delimiters or provide guidance on how to ignore instructions embedded within the target text, the agent may be vulnerable to indirect prompt injection attacks. * Ingestion points: Input text provided by the user for humanization (SKILL.md). * Boundary markers: The skill does not define specific boundaries or markers to isolate user data from instructions. * Capability inventory: The skill has access to file system tools including Read, Write, Edit, Grep, and Glob (SKILL.md frontmatter). * Sanitization: No sanitization or filtering of the input text is performed before processing.
- [EXTERNAL_DOWNLOADS]: The installation instructions in the README.md file guide the user to download the skill's source code from a third-party GitHub repository. * Reference: https://github.com/blader/humanizer.git
Audit Metadata