Academic Figure Prompt

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or safety violations were identified. The skill provides clear, structured instructions for figure design and references local documentation for style rules.- [PROMPT_INJECTION]: The skill ingests untrusted academic content to extract figure modules, representing an indirect prompt injection surface. This is considered safe due to the highly constrained JSON output schema.
  • Ingestion points: SKILL.md Step 1 (paper/section material).
  • Boundary markers: Not explicitly defined for input materials.
  • Capability inventory: The skill configuration permits the use of the bash tool.
  • Sanitization: No explicit sanitization or filtering of input content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 08:32 AM
Security Audit — agent-trust-hub — Academic Figure Prompt