us-stock-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The
scripts/stock_analyst.pyscript fetches content from external APIs, such as Twitter and web search, and incorporates this data directly into the prompts used for LLM-based investment summaries and sentiment analysis. - Ingestion points: Data retrieved from AIsa APIs is processed in the
_create_investment_summaryand_analyze_sentimentmethods inscripts/stock_analyst.py. - Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from following instructions that could be hidden within the fetched tweets or news headlines.
- Capability inventory: The script can perform network requests to
api.aisa.oneand write JSON files to the local file system. - Sanitization: Content is serialized using
json.dumps()but no specialized filtering for malicious prompts is applied to the retrieved external text.
Audit Metadata