latex-fmt

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard command-line utilities including pdflatex, bibtex, biber, and exiftool to compile documents and manage metadata. These tools are used within their intended purpose for LaTeX document processing.\n- [PROMPT_INJECTION]: The skill processes user-supplied LaTeX files (.tex), which presents a surface for indirect prompt injection. While the skill has capabilities to write to the filesystem and execute commands, the risk is mitigated by the specific scope of the formatting task.\n
  • Ingestion points: Reads content from .tex files in the user project directory.\n
  • Boundary markers: Not present. The skill does not define specific markers to distinguish between formatting content and potential adversarial instructions within the LaTeX source.\n
  • Capability inventory: File read/write access and shell command execution for LaTeX compilation and metadata management.\n
  • Sanitization: Not present. Input from LaTeX files is processed without explicit sanitization beyond the inherent parsing of the LaTeX engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 04:54 PM
Security Audit — agent-trust-hub — latex-fmt