chart-style-unifier

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill automatically fetches and installs the python-docx and pywin32 libraries from official package registries (such as PyPI or well-known mirrors) if they are not already present in the environment.\n- [COMMAND_EXECUTION]: Utilizes subprocess.run to execute pip install commands for runtime dependency management. While the packages are well-known, the use of shell commands for dynamic installation is a notable capability.\n- [INDIRECT_PROMPT_INJECTION]: A potential vulnerability surface exists because the skill ingest and processes the contents of external Word documents, which could contain malicious instructions designed to be interpreted by the AI agent.\n
  • Ingestion points: scripts/change_table_font.py opens and reads .docx files specified by the target_doc_path configuration field.\n
  • Boundary markers: No explicit delimiters or instructions to ignore instructions embedded within document content are present.\n
  • Capability inventory: The skill possesses significant capabilities including shell command execution (subprocess), file system writes (docx.save), and full Office COM automation (win32com.client.Dispatch).\n
  • Sanitization: The skill performs basic validation of file existence and extensions but does not sanitize or filter the actual content of the document paragraphs and runs before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 04:49 PM