math-figure-generator

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data artifacts and source files to generate visualization code, which introduces a surface for indirect prompt injection.
  • Ingestion points: The workflow in SKILL.md specifies reading "source artifacts" and "source files" (Step 1) to determine variables and units for plotting.
  • Boundary markers: There are no instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded within the processed data files.
  • Capability inventory: The skill uses Python code generation (via matplotlib) and file writing operations (fig.savefig in references/chart-patterns.md) to create output in paper/figures/ or results/ directories.
  • Sanitization: The instructions do not include validation or sanitization of the input data before it is incorporated into the generated plotting code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 12:52 PM
Security Audit — agent-trust-hub — math-figure-generator