figma-generate-changelog
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to parse file keys from URLs using
sedand to run local Node.js scripts for data processing. - [EXTERNAL_DOWNLOADS]: Fetches design metadata and version history from the Figma REST API (
api.figma.com). This targets a well-known service and is the primary function of the skill. - [DATA_EXPOSURE]: The skill requires a Figma Personal Access Token for authentication. It correctly instructs the user to provide this via the
FIGMA_TOKENenvironment variable rather than hardcoding it in scripts or instructions. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design data (page names, component descriptions) from the Figma API.
- Ingestion points: Figma REST API (
api.figma.com). - Boundary markers: Output is formatted into markdown sections.
- Capability inventory: Shell execution of
nodeandsedscripts. - Sanitization: The
generate-changelog.mjsscript includes anescapeMdfunction that escapes common markdown control characters (backticks, asterisks, etc.) to prevent structural breaks or injection in the generated report.
Audit Metadata