docs-latex
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses dynamic context injection to gather system environment information during loading. Evidence: The SKILL.md file executes diagnostic commands including which pdflatex, pwd, and find to check the local environment and list Markdown files.
- [EXTERNAL_DOWNLOADS]: The skill instructions include commands to download LaTeX dependencies from trusted sources. Evidence: The execution workflow uses apt-get to install texlive packages from official operating system software repositories.
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to perform its document conversion and metadata inspection tasks. Evidence: Core functionality relies on the execution of pdflatex, pdfinfo, and stat.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface by processing external user-supplied files. Ingestion points: The primary source file passed via the file argument. Boundary markers: No explicit delimiters or instructions to ignore instructions within the input file are present. Capability inventory: The skill has access to Bash, Write, and Edit tools, and executes shell commands like pdflatex. Sanitization: While the skill includes basic LaTeX character escaping, it lacks comprehensive sanitization against malicious LaTeX commands that could be embedded in Markdown to exploit features like file inclusion.
Audit Metadata