svg-illustrator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided documents or concepts to generate SVG art, creating a standard input surface for indirect injection.
- Ingestion points: The skill reads user-supplied documents and conceptual descriptions as defined in the "Execution Steps" section of SKILL.md.
- Boundary markers: There are no specific delimiters or guardrail instructions defined to separate user data from the agent's core instructions.
- Capability inventory: The skill's primary capability is generating and inserting SVG code into Markdown files. It does not possess network, file system write (beyond the document being edited), or shell execution capabilities.
- Sanitization: The instructions do not specify any sanitization or escaping of user-provided text before it is potentially incorporated into SVG labels or descriptions.
Audit Metadata