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
Bashtool 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.mdguide users to obtain thebaposter.clsfile from its public GitHub repository (github.com/mloesch/baposter). This is a standard requirement for using thebaposterclass, 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 theBashtool to perform legitimate operations related to poster production, such as compiling.texfiles and executing thescripts/review_poster.shutility, which checks PDF attributes using standard tools likepdfinfoandpdffonts.
Audit Metadata