ieee-latex

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a bash script (scripts/compile.sh) and instructions to execute pdflatex and bibtex. These tools are used to process and compile document source files into PDF format.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection through the processing of untrusted LaTeX source code.
  • Ingestion points: Untrusted LaTeX source files (main.tex) and local configuration files (workspace/src/config.py).
  • Boundary markers: No explicit markers or instructions are provided to delineate untrusted content or ignore embedded instructions within the processed files.
  • Capability inventory: The skill utilizes Bash, pdflatex, bibtex, and Grep to automate the compilation and validation process.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the input LaTeX content, which could lead to exploitation via LaTeX macros if shell-escape is enabled in the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 06:43 AM