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
.makefiles 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