text-resizing
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_&_EXFILTRATION]: No sensitive file access or unauthorized network operations detected. The skill references well-known documentation sources including the W3C (w3.org) and MDN Web Docs (mozilla.org).
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverified dependency installations were found. Code examples are static CSS and React snippets intended for reference.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze rendered HTML and interactive components, which constitutes an ingestion point for untrusted data. However, the associated capabilities are limited to standard accessibility auditing tools (accessibility tree inspection, Axe, Lighthouse) and do not include high-risk operations like arbitrary command execution or file system modifications.
- Ingestion points: Rendered HTML markup and interactive component states as described in SKILL.md.
- Boundary markers: None explicitly defined for untrusted content.
- Capability inventory: Use of browser accessibility panes, automated checkers (axe, Lighthouse), and manual keyboard/screen-reader testing.
- Sanitization: No explicit sanitization or filtering of input markup is specified.
- [PROMPT_INJECTION]: No attempts to override agent instructions or bypass safety filters were detected in the instructions or metadata.
Audit Metadata