The Agent Skills Directory

[SAFE]: The skill follows security best practices by recommending the use of environment variables (FIGMA_PAT) for sensitive credentials rather than hardcoding them. The provided code templates for the InstrumentedFigmaClient log only request metadata (status, latency, rate limits) and normalize endpoint paths to prevent sensitive ID exposure in logs and metrics.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Figma REST API. While this represents a potential attack surface for indirect prompt injection, the risk is minimal as the skill performs structured data parsing and does not use the API responses in any dynamic execution or shell commands.
Ingestion points: Figma API response bodies processed in SKILL.md and references/health-check-with-details.md.
Boundary markers: None explicitly defined for the API data stream.
Capability inventory: No subprocess calls, eval(), or unsafe file-write operations are performed on the ingested data.
Sanitization: The code includes path normalization (replace(/[a-zA-Z0-9]{15,}/, ':key')) to sanitize identifiers before they are included in logs or metrics.

figma-observability