pre-submission-report

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data (LaTeX files) which presents a surface for indirect prompt injection.
  • Ingestion points: Reads content from user-provided or auto-detected .tex files (e.g., paper/main.tex).
  • Boundary markers: The instructions lack explicit delimiters or specific warnings for the agent to disregard instructions that might be embedded within the LaTeX document content.
  • Capability inventory: The skill is granted Write access to the filesystem to save reports and Bash execution capabilities (limited to latexmk, mkdir, ls, wc).
  • Sanitization: No sanitization or escaping of the ingested document content is performed before it is processed by the agent or sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 07:17 PM