thesis-standardizer

Pass

Audited by Gen Agent Trust Hub on Jun 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Multiple Python and PowerShell scripts, such as scripts/generate_thesis_variants.py, scripts/bootstrap_thesis_project.py, and scripts/check_final_thesis_docx.ps1, execute other internal scripts or external CLI tools like officecli and git using subprocess or system calls. This is used for coordinating the complex thesis generation and validation pipeline.
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface.
  • Ingestion points: It processes untrusted user data from project source code in scripts/build_project_evidence.py and school templates in scripts/extract_docx_template_profile.py.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the ingested data.
  • Capability inventory: The skill has extensive command execution capabilities via subprocess calls in scripts such as scripts/generate_thesis_variants.py and scripts/bootstrap_thesis_project.py.
  • Sanitization: External content is used to inform LLM generation without significant filtering or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 7, 2026, 03:20 AM
Security Audit — agent-trust-hub — thesis-standardizer