skills/ujang19/agent-skill-bedul/docx/Gen Agent Trust Hub

docx

Fail

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill utilizes high-risk dynamic code generation and injection techniques. In scripts/office/soffice.py, it writes C source code to the temporary directory, compiles it using gcc, and then injects the resulting shared object into the soffice process using LD_PRELOAD to intercept system calls. Furthermore, scripts/accept_changes.py dynamically creates a LibreOffice Basic macro and writes it to a temporary user profile for execution.
  • [COMMAND_EXECUTION]: The skill executes multiple powerful system utilities through subprocess calls, providing potential attack surfaces if parameters are influenced by untrusted data. Examples include the use of gcc for runtime compilation, soffice for document processing, and git for generating document diffs.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 11, 2026, 07:05 PM