deck-beamer-academic

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security concerns identified. All components, including instructions, LaTeX assets, and helper scripts, are consistent with the stated purpose of professional slide generation.
  • [COMMAND_EXECUTION]: The provided scripts/compile.sh is a benign utility script for automating LaTeX builds using standard engines like pdflatex or lualatex. It performs routine cleanup of LaTeX auxiliary files.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) when processing external data. * Ingestion points: User-provided source material (papers, sections, results) as mentioned in SKILL.md. * Boundary markers: Absent. * Capability inventory: LaTeX generation in SKILL.md and auxiliary file cleanup in scripts/compile.sh. * Sanitization: Instructions require the agent to reason about and compress content into slides rather than blindly echoing input.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:44 PM
Security Audit — agent-trust-hub — deck-beamer-academic