accessibility-auditing
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted content from external websites via browser snapshots.
- Ingestion points: Web content is retrieved through
browser_navigateandbrowser_snapshotcommands as described inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or safety prompts to prevent the agent from accidentally executing instructions that might be embedded in the audited web pages.
- Capability inventory: The skill uses browser interaction tools and suggests performing code modifications to fix accessibility issues.
- Sanitization: The accessibility tree content retrieved from the browser is processed directly without filtering for potential prompt injection strings.
Audit Metadata