render-skill
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): No instructions designed to override behavior or bypass safety guidelines were found.
- Data Exposure & Exfiltration (SAFE): The skill does not access sensitive files or perform any network operations.
- Obfuscation (SAFE): The code is transparent and contains no encoded or hidden logic.
- Indirect Prompt Injection (INFO): Detected a surface for terminal markup injection. 1. Ingestion points: Untrusted data enters through function parameters in
render_task_table,render_task_detail, andrender_dashboard. 2. Boundary markers: Absent. 3. Capability inventory: Restricted to terminal output via the Rich library; no subprocess, network, or file system write privileges. 4. Sanitization: Absent; input strings are directly interpolated into Rich markup. This could allow an attacker to change the color or style of terminal output, but no execution or exfiltration is possible.
Audit Metadata