screen-reader
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected. The skill is designed for accessibility testing and follows standard auditing procedures.
- [NO_CODE]: The skill consists entirely of natural language instructions for the agent and does not include any scripts, commands, or executable code blocks.
- [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface because it processes untrusted webpage content (the DOM) to perform its simulation. However, the risk is negligible as the skill lacks exploitable capabilities.
- Ingestion points: The skill reads the page content in DOM order (SKILL.md).
- Boundary markers: Absent; the skill does not specify delimiters for external content.
- Capability inventory: No file system access, network operations, or subprocess executions are requested or defined in this skill.
- Sanitization: Absent; the skill relies on the agent's default processing of webpage data.
Audit Metadata