svg-logo-creator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes external data (concept briefs and brand descriptions) as input and uses it to generate SVG files, creating an attack surface for indirect prompt injection.
- Ingestion points: Input requirements in SKILL.md specify gathering brand names, taglines, and visual concepts from users or ideation briefs.
- Boundary markers: The skill lacks explicit instructions or delimiters to help the agent distinguish between legitimate design requirements and malicious instructions embedded in the input.
- Capability inventory: The SKILL.md instructions guide the agent to generate code and save files (e.g., logo-primary.svg).
- Sanitization: No sanitization or validation logic is defined to prevent malicious content from being injected into the SVG structure or metadata.
Audit Metadata