display-quantitative-information
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied CSV and JSON files through its analytical scripts, creating a surface for indirect prompt injection where malicious instructions could be embedded in data fields.
- Ingestion points:
scripts/suggest_display.pyandscripts/render_chart_svg.pyingest CSV data;scripts/audit_visual_display.pyingests JSON chart specifications. - Boundary markers: The instructions do not explicitly mandate that the agent ignore natural language instructions discovered within the data contents of these files.
- Capability inventory: The skill is restricted to analytical outputs and SVG generation. It lacks network access, file-write capabilities (beyond the output path), and shell execution.
- Sanitization: The
render_chart_svg.pyscript correctly useshtml.escapewhen embedding data values into SVG text tags, mitigating certain injection vectors.
Audit Metadata