market-watch
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process real-time market data provided as 'ambient' information. This creates a surface where the external data source could theoretically attempt to influence agent behavior through embedded instructions in the feed.
- Ingestion points: The skill explicitly processes automated price updates delivered via
<market-watch>blocks appended to the conversation. - Boundary markers: External data is delimited using
<market-watch>XML-style tags. - Capability inventory: The agent uses tools including
watch_market,get_quote, andschedule_wakeup, along with standard file-writing capabilities to generate deliverables. - Sanitization: The instructions do not specify a sanitization or validation process for the content of the market feed blocks.
Audit Metadata