wewrite-rewrite

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the wewrite CLI tool to perform content scoring (wewrite score) and similarity analysis (wewrite similarity) against source documents as part of its quality gate process.
  • [EXTERNAL_DOWNLOADS]: Instructions include guidance to install the necessary wewrite utility via the uv package manager or a local installation script if the tool is not already present in the system environment.
  • [PROMPT_INJECTION]: The skill processes user-supplied text which presents an ingestion surface for indirect prompt injection, though this is managed by the skill's specific transformation tasks.
  • Ingestion points: User articles are saved to source.md within the task directory (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified.
  • Capability inventory: The skill is authorized to use Bash for command execution, alongside Read, Write, Edit, and Glob for file operations (SKILL.md).
  • Sanitization: No content sanitization or filtering is mentioned in the instructions for the external article content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 08:21 AM
Security Audit — agent-trust-hub — wewrite-rewrite