figma-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes external document data from the Figma API, which could theoretically contain instructions intended to influence the agent's behavior.
  • Ingestion points: The skill retrieves JSON data representing Figma files and nodes from https://api.figma.com/v1/files/ in SKILL.md and references/typescript-hello-world.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the fetched Figma data as untrusted or to ignore any natural language instructions embedded within layer names or metadata.
  • Capability inventory: The skill has access to powerful tools including Bash(curl), Bash(node), Bash(npx), Read, Write, and Edit as specified in the frontmatter.
  • Sanitization: The provided shell and TypeScript examples do not implement sanitization or validation of the API response before the data is processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:45 AM
Security Audit — agent-trust-hub — figma-hello-world