bigdata-skill
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves financial news chunks and transcript data from Bigdata.com, which constitutes an ingestion surface for untrusted external content that could contain embedded instructions.
- Ingestion points: Data is retrieved via
AnnotatedSearcher.search(scripts/bigdata_toolkit/search.py) andStructuredDataRESTmethods (scripts/bigdata_toolkit/rest_ext.py). - Boundary markers: The skill does not implement specific delimiters or instructions to isolate retrieved news text from the agent's system prompt.
- Capability inventory: The skill possesses network capabilities (via the
requestslibrary) to interact with the service API and S3 presigned URLs for batch operations. - Sanitization: No sanitization or filtering of the retrieved content is performed to detect or remove malicious prompt injection patterns before the data is processed by the agent.
Audit Metadata