agentbets
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [Data Exposure & Exfiltration] (LOW): The skill performs network requests using
fetch()tohttps://agentbets-api-production.up.railway.app, which is not a whitelisted domain for network operations.\n- [Indirect Prompt Injection] (LOW): The skill ingests market data from an external API and displays it to the agent, creating a surface for potential instruction injection.\n - Ingestion points: API responses from the
/markets,/markets/:id, and/opportunitiesendpoints are processed inindex.ts.\n - Boundary markers: Absent. Data from the API is directly interpolated into the output strings.\n
- Capability inventory: None. The skill only performs read-only network operations and logging. No subprocess spawning, file writing, or dynamic execution (eval/exec) was detected.\n
- Sanitization: Absent. The skill does not validate or sanitize strings like
m.questionorm.descriptionbefore including them in the response.
Audit Metadata