alterlab-latex-posters

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to integrate user-provided research text and data into LaTeX poster templates, which creates a potential injection surface if the input contains malicious LaTeX commands.\n
  • Ingestion points: User-supplied research findings, text, and figure descriptions are interpolated into LaTeX source files provided in the assets/ directory.\n
  • Boundary markers: The skill does not implement specific boundary markers or instructions to the agent to treat user data as untrusted text during interpolation.\n
  • Capability inventory: The skill utilizes the Bash tool to execute LaTeX compilation commands and run PDF analysis tools.\n
  • Sanitization: There is no evidence of explicit sanitization or validation of user-provided content before it is included in the LaTeX templates.\n- [EXTERNAL_DOWNLOADS]: The skill instructions in SKILL.md guide users to obtain the baposter.cls file from its public GitHub repository (github.com/mloesch/baposter). This is a standard requirement for using the baposter class, as it is not distributed in official TeX repositories, and GitHub is recognized as a well-known and trusted service for source code distribution.\n- [COMMAND_EXECUTION]: The skill employs the Bash tool to perform legitimate operations related to poster production, such as compiling .tex files and executing the scripts/review_poster.sh utility, which checks PDF attributes using standard tools like pdfinfo and pdffonts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:37 PM