brandfy-setup
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads from and updates the project's instruction files (e.g., AGENTS.md), creating a surface where project data could influence the agent's behavior. \n
- Ingestion points: The script reads from AGENTS.md, .brandfy/ configuration files, and internal reference documents.\n
- Boundary markers: The script uses specific HTML-style comment tags and to delimit the instructions it injects.\n
- Capability inventory: The skill has the ability to create directories, write multiple configuration and markdown files, and instructs the agent to execute a bundled Node.js script.\n
- Sanitization: No explicit content sanitization or escaping is performed on the data gathered from the project environment before it is merged into the agent's instruction sets.\n- [COMMAND_EXECUTION]: The skill requires the agent to execute a bundled Node.js script (scripts/setup.mjs) to manage the project's filesystem structure and perform initialization tasks.
Audit Metadata