canva-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as release artifacts, configuration versions, and OpenAPI specifications using the
ReadandGreptools. This creates a potential surface for indirect prompt injection if the analyzed files contain malicious instructions aimed at the agent. - Ingestion points: Release artifacts, configuration files, and OpenAPI changelogs read during the verification steps.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill has access to
Read,Grep,Write, andEdittools. - Sanitization: There is no mention of sanitizing or validating the contents of external files before processing.
- [EXTERNAL_DOWNLOADS]: The skill refers to official Canva developer documentation and security guidelines (canva.dev). These references are for informational purposes and originate from well-known and trusted service domains.
Audit Metadata