libreoffice-writer

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill launches the LibreOffice binary in headless mode using subprocess.Popen in scripts/uno_bridge.py. This is a core part of its functionality used to establish a UNO bridge for document manipulation. The command uses a hardcoded list of safe arguments and does not involve a shell.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its document reading capabilities.
  • Ingestion points: Document text is read via read_text in scripts/writer/session.py and returned to the agent.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are used when document content is interpolated into the agent's context.
  • Capability inventory: The skill has the ability to write to the file system, delete document content, and execute the LibreOffice process.
  • Sanitization: Document content is processed as raw text without validation or sanitization against embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 08:42 AM
Security Audit — agent-trust-hub — libreoffice-writer