frontend-design-master
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes scripts (
scripts/ux_audit.pyandscripts/accessibility_checker.py) to analyze the user's project directory, which introduces a potential surface for indirect prompt injection. - Ingestion points: The audit scripts read content from local HTML, JSX, and TSX files in the project directory and report findings to the agent.
- Boundary markers: Absent. The scripts output findings directly to the agent's context without distinct delimiters or instructions to ignore embedded commands.
- Capability inventory: The agent is equipped with file system access (read/write) and shell execution capabilities.
- Sanitization: Absent. The scripts perform basic regex analysis but do not sanitize the input files against adversarial instructions.
- [EXTERNAL_DOWNLOADS]: The
install.shscript and theSKILL.mdmetadata reference the author's public GitHub repository for installation and updates. These references are documented neutrally as standard distribution mechanisms for the skill and are sourced from the verified author's account.
Audit Metadata