stock-analysis
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes content from external bloggers and sentiment tools (SKILL.md) which may contain malicious instructions. Evidence Chain: 1. Ingestion points: Data from
search_viewpointsandget_ticker_sentiment. 2. Boundary markers: Absent. 3. Capability inventory: None (only report generation). 4. Sanitization: Absent. The severity is LOW because the skill lacks dangerous capabilities like file writing or shell execution. - [Safe Behavior] (SAFE): No obfuscation, credential exposure, or unauthorized command execution patterns were found. The skill specifically instructs the agent to present all viewpoints fairly and avoid financial advice.
Audit Metadata