geo-human-editor
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local Python utility
scripts/humanize_content.pyto automate the editing process. - Evidence: The script performs standard file read and write operations on paths provided via CLI arguments (
--input,--output). - [PROMPT_INJECTION]: The skill processes user-provided text content, which is a potential surface for indirect prompt injection.
- Ingestion points: Text content read from the local file system by the humanization script.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are used in the provided prompt logic or script.
- Capability inventory: File system read/write access via the Python script.
- Sanitization: The script performs basic string replacements for vocabulary and formatting but does not filter for malicious instruction sequences.
Audit Metadata