humanize-chinese
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize specific command-line sequences to process text files using external Python scripts. Evidence: The "Optional CLI Flow" section details commands such as
python3 scripts/detect_cn.py text.txt -vandpython3 scripts/style_cn.py text.txt --style xiaohongshu -o out.txt. - [PROMPT_INJECTION]: The skill processes untrusted input data, which creates a surface for indirect prompt injection where instructions embedded in the input could influence agent behavior. Ingestion points: User-provided Chinese text files (e.g.,
text.txt,paper.txt) are ingested for processing. Boundary markers: Absent; there are no instructions to use delimiters or specifically ignore embedded commands. Capability inventory: The skill uses shell commands (python3) to read and manipulate files. Sanitization: Absent; the skill does not specify any validation or filtering of the input content before processing.
Audit Metadata