json-canvas
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a functional reference for the JSON Canvas format, specifying data structures for nodes and edges without involving dangerous commands or system modifications.
- [EXTERNAL_DOWNLOADS]: The skill links to the official JSON Canvas project website and repository on GitHub. These references are to well-known resources and do not involve remote script execution or untrusted packages.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading and parsing .canvas files (Ingestion points: SKILL.md). It relies on strict JSON schema validation rather than content delimiters (Boundary markers: absent). The agent uses file-read and file-write operations (Capability inventory: SKILL.md) while verifying structural integrity (Sanitization: SKILL.md).
Audit Metadata