make-poster

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python scripts (poster_size.py, poster_figures.py, poster_lint.py, pitch_check.py) to process local files and calculate poster dimensions. These scripts use standard Python libraries, perform basic file I/O on provided paths, and do not execute arbitrary shell commands or access sensitive system paths.
  • [DATA_EXPOSURE]: The scripts operate purely on user-provided LaTeX or Markdown files within the workspace. No network operations or credential access patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided paper sources (.tex files) and pitch drafts. While it lacks explicit boundary markers, its capabilities are restricted to local file processing and reporting, minimizing the risk of a capability-based attack.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 01:02 PM
Security Audit — agent-trust-hub — make-poster