trade-analyze
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a legitimate financial analysis orchestrator, using internal tools to collect and synthesize public market data.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive local files, credentials, or environment variables are accessed. The skill only processes public financial data and writes a summary report to the local directory.
- [PROMPT_INJECTION]: The instructions provide a clear framework for the AI agent to act as a financial analyst. There are no attempts to bypass safety filters or override core instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web data.
- Ingestion points: WebSearch results in SKILL.md.
- Boundary markers: Absent; data is organized into a DISCOVERY_BRIEF but without isolation warnings.
- Capability inventory: Writes report files to the filesystem and launches sub-agents.
- Sanitization: Absent. While the surface exists, the risk is localized to the generated report content.
Audit Metadata