meetless-design-system
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's prototypes and documentation reference Google Fonts (fonts.googleapis.com and fonts.gstatic.com) to load the Inter and Berkeley Mono font families. This is a standard and safe practice for web-based design systems.
- [COMMAND_EXECUTION]: The SKILL.md file contains a verification section that instructs users to run an audit tool (design-system-package-audit) using platform-specific environment variables. This is a legitimate development workflow used to ensure package compliance.
- [INDIRECT_PROMPT_INJECTION]: The interactive prototypes (e.g., examples/meetless-prototype.html) include an 'Ask' feature that processes meeting transcripts and user queries, presenting an inherent surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through the transcription segments and the user's question input field (askInput).
- Boundary markers: The system does not currently use specific delimiters or instructions to separate transcript content from user queries in the prompt logic.
- Capability inventory: The prototype is a static HTML/JS demonstration and lacks access to dangerous capabilities such as file system writes, network requests, or subprocess execution.
- Sanitization: The prototype code includes a robust 'esc()' function that escapes HTML special characters before rendering data to the DOM, mitigating cross-site scripting (XSS) and similar injection risks.
Audit Metadata