stocks
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external financial APIs, which creates an attack surface for indirect prompt injection if a ticker name or company description contains malicious instructions.
- Ingestion points: The
scripts/stocks_client.pyfile fetches data fromquery1.finance.yahoo.com,query2.finance.yahoo.com, andwww.alphavantage.co. - Boundary markers: The skill outputs results in a structured JSON format, but it does not provide explicit instructions to the agent to ignore or delimit potentially adversarial content within the data fields.
- Capability inventory: The skill is executed via the
terminaltool, allowing the agent to run the Python script and view its output. - Sanitization: While the script handles JSON parsing and numeric formatting, it does not include logic to filter or sanitize natural language strings from the API responses for injection patterns.
Audit Metadata