alpha-vantage
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
requestsandpandaslibraries. These are official, well-known, and highly reputable packages from the Python Package Index (PyPI) used for data manipulation and HTTP communication. - [PROMPT_INJECTION]: The skill processes financial data retrieved from the Alpha Vantage API (alphavantage.co), which acts as an ingestion point for untrusted external content. This creates a surface for indirect prompt injection.
- Ingestion points: External JSON data retrieved via the
av_getfunction inSKILL.md. - Boundary markers: None identified; instructions do not advise the agent to treat API responses as untrusted data.
- Capability inventory: The skill uses
requestsfor network GET operations andprintfor outputting data. It does not possess high-risk capabilities like file system writes, shell command execution, or persistence mechanisms. - Sanitization: None; the skill processes the raw JSON response from the API.
- [DATA_EXFILTRATION]: The skill requires the use of an
ALPHAVANTAGE_API_KEY, which is transmitted to the officialalphavantage.codomain for authentication. This is standard, intended functionality for an API wrapper and does not constitute unauthorized exfiltration.
Audit Metadata