blog-chart

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides templates and instructions for creating various SVG chart types (bar, donut, line, etc.) with accessible attributes and styling. It does not perform any sensitive operations such as network requests, file system modifications, or shell command execution. The referenced styling document is a local markdown file used for design consistency.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies an ingestion surface where data metrics and chart titles provided by other workflows are interpolated into SVG elements like <title> and <desc>. However, there are no exploitable capabilities (network, command execution) associated with this skill, and the generated output is static XML/JSX text.\n
  • Ingestion points: SKILL.md (Chart Request section).\n
  • Boundary markers: Absent.\n
  • Capability inventory: No command execution, file writes, or network operations detected in SKILL.md.\n
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:43 AM