canva-brand-check
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted design content (text and visual data) which presents a surface for indirect prompt injection if an attacker embeds instructions within a Canva design.
- Ingestion points: Design text retrieved via
Canva:get-design-contentand element metadata fromCanva:start-editing-transaction(SKILL.md). - Boundary markers: The skill does not currently define clear delimiters or explicit instructions to ignore embedded commands within the processed design data.
- Capability inventory: The agent has the ability to modify designs via
canva-edit-design, though the skill instructions specify this should only be done as an offer to the user after the report (SKILL.md). - Sanitization: No specific filtering or validation of text content from the design is mentioned before processing.
Audit Metadata