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
Risk Level
SAFE
Analyzed
May 3, 2026, 02:40 PM