insider-trading-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external financial market data, company announcements, and transaction records retrieved from tools like
findata-toolkit-cnand public financial portals.\n - Ingestion points: External data regarding insider trades, management roles, and company performance is processed to generate analytical reports (SKILL.md).\n
- Boundary markers: The skill instructions and output templates (references/output-template.md) provide structure but do not include explicit delimiters or instructions to ignore potential commands embedded within the external data strings.\n
- Capability inventory: The skill acts as an analytical layer and does not possess capabilities for file system modification, shell command execution, or unauthorized network exfiltration within its own provided logic.\n
- Sanitization: There are no defined mechanisms for sanitizing or filtering the content of the ingested market data for malicious prompt injection patterns.
Audit Metadata