soia-dev-officecli-ops

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill initiates subprocesses to run the officecli executable. These calls are implemented using list-based arguments, which prevents shell command injection.\n- [EXTERNAL_DOWNLOADS]: The documentation directs users to the GitHub repository for OfficeCLI (iOfficeAI/OfficeCLI) for manual installation. No automated downloading or execution of remote scripts is performed by the skill itself.\n- [PROMPT_INJECTION]: Vulnerability to indirect prompt injection through the processing of external Office documents.\n
  • Ingestion points: Input files provided to scripts/officecli_inspect.py and scripts/officecli_safe.py.\n
  • Boundary markers: Absent; there are no specific instructions to the agent to ignore embedded commands within the files.\n
  • Capability inventory: File reading, structural modification, and schema validation via the officecli tool as seen in scripts/officecli_inspect.py and scripts/officecli_safe.py.\n
  • Sanitization: Subprocess calls use argument lists rather than shell strings, providing protection against typical injection attacks at the command line level.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 08:03 AM
Security Audit — agent-trust-hub — soia-dev-officecli-ops