json-canvas
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely descriptive, providing a specification for the JSON Canvas file format. It does not include any scripts, binary files, or tool invocations.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data into Markdown nodes. However, as it includes no external tools or executable code, the risk is negligible.
- Ingestion points: User-provided text for text nodes and external URLs for link nodes as described in SKILL.md.
- Boundary markers: Not specified.
- Capability inventory: The skill specifies no allowed-tools or scripts, limiting agent actions to text generation.
- Sanitization: Mentions newline escaping for JSON validity, but no security-focused sanitization of user-provided content.
Audit Metadata