stock-fund
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided stock names or codes, creating an ingestion point for potentially untrusted data that is then passed to external tools.
- Ingestion points: User input provided as a stock name or code via the command argument described in
SKILL.md. - Boundary markers: Absent. The instructions do not specify any delimiters or safety guardrails to separate user input from the rest of the prompt context.
- Capability inventory: The skill performs tool calls (
get_stock_fund_flow,get_fund_flow_rank,get_market_fund_flow) based on the provided input. - Sanitization: Absent. There is no mention of input validation or sanitization before the stock identifier is processed.
Audit Metadata