5writing

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a template manager for writing academic-style papers in Typst. It includes a comprehensive set of templates for various mathematical modeling competitions (MCM/ICM, CUMCM, etc.).
  • [COMMAND_EXECUTION]: The skill uses basic shell commands (ls, cp) to verify template existence and prepare the workspace. These operations are restricted to the skill's own directory and the output directory, which is standard for file management tasks.
  • [DATA_EXPOSURE]: The skill processes data from report files (RESULTS_REPORT.md, ANALYSIS_MODELING_REPORT.md) produced in earlier stages. This is the intended behavior for a documentation skill and does not involve unauthorized data access or exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from generated reports into paper templates. While this is an attack surface, the risk is inherent to the task of summarizing analysis results, and the skill includes instructions to ensure data accuracy and avoid fabrication.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:07 AM
Security Audit — agent-trust-hub — 5writing