manuscript-typography
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructional guidelines for an AI agent to review and audit LaTeX files (.tex) and log files (.log) for typographic errors and formatting consistency.
- [DATA_EXPOSURE]: The skill accesses project-specific files (.tex, .log) which is necessary for its stated purpose of manuscript auditing. No sensitive system paths or credentials are accessed.
- [COMMAND_EXECUTION]: While the skill mentions using 'grep' to find patterns in LaTeX log files, this is a standard text-searching operation within the context of a development tool and does not represent arbitrary command execution or shell injection risks.
- [EXTERNAL_DOWNLOADS]: The skill recommends various LaTeX packages (e.g., microtype, booktabs, siunitx) for the user to include in their LaTeX projects. These are well-known, standard packages in the TeX ecosystem and are not downloaded or executed by the agent itself.
- [PROMPT_INJECTION]: There are no patterns suggesting attempts to override system prompts or bypass safety filters. The instructions are strictly limited to the domain of academic typography.
Audit Metadata