canva-resize-for-all-social-media
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No security issues detected. The skill follows best practices for automated workflows within a constrained tool environment.
- Indirect Prompt Injection (LOW): The skill processes user-provided design names and URLs. While this presents a theoretical surface for indirect prompt injection (e.g., a design title containing malicious instructions), the impact is limited by the specific toolset (Canva API) and the lack of high-risk capabilities like arbitrary shell execution or broad network access.
- Ingestion points: User input (design ID/URL/name) and API responses (design titles).
- Boundary markers: None explicitly defined for interpolated design names.
- Capability inventory: Limited to
get-design,search-designs,resize-design, andexport-designtools. - Sanitization: None observed for design metadata.
Audit Metadata