responsive-size
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it audits images and attributes within codebase files (HTML and React components). However, the risk is negligible because the skill's capabilities are restricted to analysis and reporting, with no dangerous actions like file writing or network communication.\n
- Ingestion points: Audits tags and CSS properties in HTML and React component files as specified in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters to isolate the audited code from the agent's instructions.\n
- Capability inventory: The skill is limited to reading code and generating descriptions or recommended fixes; it contains no subprocess calls, network operations, or file system modifications.\n
- Sanitization: There are no instructions for sanitizing or escaping the content read from the codebase.\n- [SAFE]: The skill serves as a best-practice guide for frontend performance optimization. All code examples for image resizing and DOM auditing use standard libraries (e.g., sharp) and browser APIs for their intended developer-facing purposes.\n- [SAFE]: References and source URLs point to frontendchecklist.io, which is a recognized community resource for web development best practices.
Audit Metadata