latex-document-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill includes a 'Core Constraints' section that explicitly forbids the execution of LaTeX compilation commands such as
pdflatex,xelatex, andlatexmk. This prevents the agent from triggering potentially dangerous shell-escape features within LaTeX environments. - [DATA_EXFILTRATION] (SAFE): Analysis of the skill body and referenced style guide shows no network-based commands (curl, wget) or access to sensitive local directories (e.g., ~/.ssh, ~/.env).
- [EXTERNAL_DOWNLOADS] (SAFE): The skill does not attempt to install external packages or download scripts from remote sources. It relies on standard LaTeX environments and local file structures.
- [PROMPT_INJECTION] (SAFE): The instructions are strictly limited to document formatting, structure, and writing style. There are no patterns suggesting attempts to bypass AI safety guidelines or override system-level constraints.
- [REMOTE_CODE_EXECUTION] (SAFE): No dynamic code execution or remote execution patterns were found. The skill's functionality is restricted to text manipulation and file writing.
Audit Metadata