chinese-quote-converter

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires running a local Python script (scripts/convert_quotes.py) to perform its primary function. The script was audited and found to use only standard Python libraries (argparse, re, pathlib) for regex-based text transformation and file I/O. It does not invoke subshells or execute external binaries.\n- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by processing external text files and outputting the result to the agent.\n
  • Ingestion points: Text data is read from user-specified file paths into memory via scripts/convert_quotes.py (line 98) using Path.read_text().\n
  • Boundary markers: No delimiters or safety instructions are used when reading or outputting the file content to prevent the agent from obeying instructions embedded in the processed text.\n
  • Capability inventory: The script has the capability to read and write files on the local filesystem (including in-place modification), but it lacks network access or the ability to execute arbitrary shell commands.\n
  • Sanitization: The script performs character replacement for typography but does not validate or sanitize the input text for malicious prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 03:08 PM