find-xemm-opps
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a prerequisite check script from the official hummingbot GitHub organization. This is a trusted vendor resource used for environment validation. \n- [REMOTE_CODE_EXECUTION]: The workflow includes a command to download and execute a shell script via bash process substitution. This is performed from a trusted vendor repository as part of the skill's initialization. \n- [COMMAND_EXECUTION]: The skill instructions guide the user to run the provided Python script (find_xemm_opps.py) to perform market analysis on configured exchange connectors. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes market data from external exchange APIs, which is then displayed to the agent. This represents an ingestion point for untrusted data. \n
- Ingestion points: scripts/find_xemm_opps.py fetches order book snapshots and trading rules via API calls. \n
- Boundary markers: Data is displayed in plain text tables without delimiters or instructions to ignore embedded commands. \n
- Capability inventory: The skill performs network requests to the local API and reads local environment configuration files (.env). \n
- Sanitization: Market data is parsed as JSON; however, string fields are not sanitized for potential prompt injection content before being presented to the agent.
Audit Metadata