polish-tables-figures

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill. The instructions and scripts focus exclusively on LaTeX formatting and color accessibility analysis.
  • [SAFE]: The provided Python scripts (check_floats.py, palettes.py, and venueyaml.py) are well-written and use only the Python standard library. They do not involve any network calls, subprocess execution, or unsafe dynamic code execution like eval() or exec().
  • [SAFE]: The skill processes user-supplied LaTeX files and logs deterministically. The file reading logic in check_floats.py includes safety checks, such as a recursion depth limit and tracking seen files, to prevent resource exhaustion or infinite loops when following LaTeX \input commands.
  • [SAFE]: The venueyaml.py script implements a custom, restricted YAML parser for venue profiles, avoiding the security risks associated with full-featured YAML parsers.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in any of the skill's files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 06:16 PM
Security Audit — agent-trust-hub — polish-tables-figures