accessibility
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- SAFE (SAFE): No malicious behaviors, prompt injections, or data exfiltration attempts were found in the documentation or agent instructions.
- Indirect Prompt Injection (SAFE): The auditor agent reads local source code using the Read and Grep tools. While this represents a data ingestion surface, the agent's instructions are focused on generating structured reports and do not involve unsafe interpolation or dynamic code execution.
- No Code (SAFE): The skill consists entirely of markdown files and agent configuration, without any bundled Python or Node.js scripts, ensuring no external code is executed.
- Data Exposure (SAFE): No sensitive file paths, hardcoded credentials, or unauthorized network operations were identified.
Audit Metadata