renhua
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute a bundled Python helper script (scripts/renhua_lint.py). This script performs static analysis on user-provided text using regular expressions to identify prohibited stylistic patterns. The script relies solely on standard Python libraries (argparse, json, re, pathlib) and does not perform network operations or access sensitive system paths. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text drafts from users. This introduces a surface for indirect prompt injection where instructions could be embedded in the technical drafts. However, the skill mitigates this risk through a well-defined operating scope, specific exclusion criteria (e.g., refusing academic or legal documents), and a workflow that prioritizes factual extraction over executing embedded directives.
Audit Metadata