brand-alchemy
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to execute a bundled Python script (
scripts/domain_checker.py) using theBashtool to perform domain availability lookups. - [EXTERNAL_DOWNLOADS]: The
domain_checker.pyscript connects to therdap.orgservice to fetch domain registration information.rdap.orgis a recognized well-known service for domain data. - [EXTERNAL_DOWNLOADS]: The bundled domain checker script disables SSL certificate verification (
ssl.CERT_NONE) when making requests to the RDAP service. - [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by ingesting user-provided brand details and using AI-generated names as shell command arguments without explicit sanitization or boundary markers. * Ingestion points: User input captured during 'The Interrogation' phase in
SKILL.md(Step 1). * Boundary markers: Absent. * Capability inventory: Subprocess calls via theBashtool for running the Python script. * Sanitization: None provided for the generated names before shell execution.
Audit Metadata