analyse-smartmoney-darkpool
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch market data and ZIP/CSV files from squeezemetrics.com and finra-markets.morningstar.com. These are established financial data sources relevant to the skill's purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for processing untrusted data from external websites.
- Ingestion points: The agent fetches data from
https://squeezemetrics.com/monitor/download/dix.zipandhttps://finra-markets.morningstar.com/finra/finia_finra_short_volume.jsp(as defined in SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands embedded within the external data sources.
- Capability inventory: The agent is granted capabilities to fetch and parse external content to produce a market verdict (ACCUMULATING/DISTRIBUTING/NEUTRAL).
- Sanitization: There are no specified sanitization or validation steps for the remote content before it is incorporated into the agent's reasoning process.
Audit Metadata