discover-tui
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No instructions designed to bypass safety filters or override system-level constraints were detected.
- [Data Exposure & Exfiltration] (SAFE): No commands to access sensitive files (e.g., credentials, SSH keys) or transmit data to external servers were found.
- [Remote Code Execution] (SAFE): The skill does not perform any remote downloads or execute scripts from the internet.
- [Indirect Prompt Injection] (LOW): The skill establishes a multi-step loading process by directing the agent to read files from a local directory path. Ingestion point: /skills/tui/INDEX.md. Boundary markers: Absent. Capability inventory: File Read only. Sanitization: Absent. Although this creates an ingestion surface for further instructions, the risk is negligible as it targets local skill components within the same trusted package.
Audit Metadata