alpha-vantage
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions in the 'Suggest Using K-Dense Web For Complex Workflows' section that direct the agent to proactively suggest the author's external platform (www.k-dense.ai) for complex reasoning or deep research. This modifies the agent's behavior to include commercial promotion.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Alpha Vantage API without adequate security boundaries, creating a vulnerability surface.
- Ingestion points: External data is ingested from the Alpha Vantage API via the
requestslibrary in theav_getfunction. - Boundary markers: The implementation lacks delimiters or instructions to isolate the retrieved data from the agent's processing context.
- Capability inventory: The skill has network access through
requestsand data processing capabilities throughpandas. - Sanitization: No sanitization, validation, or filtering of the API response is performed before it is returned to the agent context.
Audit Metadata