academic-defense-beamer

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted LaTeX source files from user-provided thesis repositories, which creates a surface where embedded instructions could attempt to influence agent behavior during the planning or Q&A preparation phases.
  • Ingestion points: scripts/extract_thesis.py and scripts/tex_loader.py read content from the user's thesis repository.
  • Boundary markers: Present. SKILL.md and agents/qa-committee-agent.md contain explicit instructions for the agent to treat thesis data as untrusted and to ignore any commands found within it.
  • Capability inventory: The skill uses subprocess.run to execute local commands in scripts/build_deck.py, scripts/typst_backend.py, and scripts/check_typst.py.
  • Sanitization: Present. The skill implements dedicated escaping logic (tex_escape, ty_literal) in scripts/build_deck.py and scripts/typst_backend.py to sanitize untrusted content before inserting it into output templates.
  • [COMMAND_EXECUTION]: The skill executes local system commands to compile LaTeX and Typst documents and to query document metadata.
  • Evidence: scripts/build_deck.py, scripts/typst_backend.py, and scripts/check_typst.py use the subprocess.run function to invoke latexmk and typst binaries.
  • Context: These executions are fundamental to the skill's primary purpose of generating PDFs. The skill constructs these commands using controlled logic and includes checks to ensure only local, pre-installed packages are used.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 03:29 AM