latex-polish
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run the
pdflatexcommand in the shell to verify that edits have not introduced compilation errors. This is a standard and appropriate use of system tools for the task. - [PROMPT_INJECTION]: The skill is designed to ingest and process text from external
.texfiles. This represents an indirect prompt injection surface where instructions embedded within a document could attempt to manipulate the agent's output. However, the skill provides extensive guardrails and a clear separation between LaTeX commands and editable text to mitigate this risk.
Audit Metadata