design-auditor
Warn
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation requires the installation of the full implementation from an external third-party repository: https://github.com/Ashutos1997/claude-design-auditor-skill.- [COMMAND_EXECUTION]: The skill provides shell commands (using npx, grep, and test) to verify the installation status and perform the setup of external code.- [PROMPT_INJECTION]: The instructions explicitly guide the agent to use the '!' command prefix (e.g., '!npx skills add...') to execute shell commands directly within the agent's environment without requiring the user to leave the conversation. This encourages autonomous execution of administrative tasks.- [PROMPT_INJECTION]: As the skill is designed to process and audit design code or assets provided by the user, it possesses an inherent attack surface for indirect prompt injection, where malicious instructions embedded in the audited files could influence the agent's behavior.
Audit Metadata