jingswap-cycle-agent
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Hiro API and Pyth oracle) to provide action recommendations to the agent. This represents an attack surface for indirect prompt injection; however, the risk is minimized by the use of established infrastructure providers and the requirement for manual user confirmation before executing any recommended actions. \n
- Ingestion points:
jingswap-cycle-agent.tsfetches blockchain state and oracle prices fromhttps://api.hiro.soandhttps://hermes.pyth.network. \n - Boundary markers: Data is returned in a structured JSON format and the
AGENT.mdinstructions explicitly mandate a confirmation step for the parent agent. \n - Capability inventory: The script performs network reads and outputs execution parameters but lacks autonomous transaction signing or system-level write access. \n
- Sanitization: The tool performs explicit type conversion and validation on the hexadecimal and numeric data received from the APIs before including it in the output rationale.\n- [EXTERNAL_DOWNLOADS]: The skill fetches configuration and live market data from well-known services, specifically the Hiro Stacks API and the Pyth Hermes oracle. These are standard resources for Stacks-based DeFi applications.
Audit Metadata