compare
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No evidence of instructions to bypass safety filters or override system behavior.
- Data Exposure & Exfiltration (SAFE): No access to sensitive files or hardcoded credentials detected.
- Obfuscation (SAFE): No hidden or encoded content found.
- Remote Code Execution (SAFE): No external downloads or script executions identified.
- Indirect Prompt Injection (SAFE): The skill ingests untrusted data via search_viewpoints and get_ticker_sentiment. Ingestion points: tool outputs. Boundary markers: absent. Capabilities: text formatting and table generation only. Sanitization: absent. The risk is considered safe as the skill lacks exploitable capabilities.
Audit Metadata