solo-humanize
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted text from files or user input, which presents a surface for indirect prompt injection where embedded instructions could potentially influence the agent. 1. Ingestion points: File content specified via arguments or text pasted by the user. 2. Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the target text. 3. Capability inventory: The skill uses Read, Write, Edit, Glob, and Grep tools for local file manipulation. 4. Sanitization: No explicit sanitization or validation of the input text is performed before processing.
- [SAFE]: The skill's primary logic is instructional and focused on linguistic transformation, with no evidence of malicious code, data exfiltration, or persistence mechanisms. The use of file system tools is restricted to the skill's stated purpose of editing local documents.
Audit Metadata