figma-make-extractor

Fail

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs cloning a repository from an unverified third-party source (https://github.com/albertsikkema/figma-make-extractor.git).
  • [REMOTE_CODE_EXECUTION]: Instructions include executing a shell script (./run-all.sh) from the cloned repository. This script performs automated dependency installation and executes unverified logic on the host system.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (git clone, npm install, ./run-all.sh) to manage files and execute the extraction pipeline.
  • [PROMPT_INJECTION]: The skill ingests untrusted .make files containing source code and AI chat history. It serves as an ingestion point for untrusted data without defined boundary markers or sanitization, creating a surface for indirect prompt injection attacks.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 15, 2026, 12:04 PM
Security Audit — agent-trust-hub — figma-make-extractor