figma-to-generateblocks
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data including Figma URLs, screenshots, and CSS, which could contain malicious instructions or hidden payloads targeting the agent's behavior.
- Ingestion points: The skill ingests design data from Figma URLs, visual screenshots, and CSS snippets provided by the user (SKILL.md).
- Boundary markers: Absent; the instructions do not include specific delimiters or guidelines to ignore instructions embedded within the design inputs.
- Capability inventory: The skill is instructed to write converted content to local .html files. It does not contain instructions for subprocess execution, network exfiltration, or dynamic code evaluation.
- Sanitization: Absent; there are no requirements for the agent to sanitize or validate extracted URLs or text content before including them in the generated block code.
Audit Metadata