xiaohongshu-rewrite

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/rewrite.py) to parse rules from a markdown file. This script uses only standard Python libraries (os, re, sys) and performs no network or sensitive file system operations beyond reading its own assets.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions by interpolating user-provided text into a style-transformation workflow. This creates a standard surface for indirect prompt injection where malicious instructions inside the user's source text could theoretically influence the output style or content.
  • Ingestion points: User-supplied text provided for rewriting in SKILL.md step 1.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to the model to ignore control sequences within the user input.
  • Capability inventory: Executes local Python scripts and reads local markdown files.
  • Sanitization: No input sanitization or filtering is performed on the user-provided text before it is processed by the transformation rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:20 PM
Security Audit — agent-trust-hub — xiaohongshu-rewrite