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.mdspecifies 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.savefiginreferences/chart-patterns.md) to create output inpaper/figures/orresults/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