evm
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external, untrusted sources including blockchain RPC providers and public directory APIs (CoinGecko, ensideas.com, and 4byte.directory). This content is returned to the agent's context where it could potentially influence its behavior if malicious instructions are embedded in blockchain metadata or transaction parameters.\n
- Ingestion points: Data enters the system via network requests in
_http_getand_http_postfunctions withinscripts/evm_client.py.\n - Boundary markers: The script returns raw or structured JSON data without explicit delimiters or instructions for the agent to disregard potential commands found within the data.\n
- Capability inventory: The skill possesses network communication capabilities (
urllib.request) and is executed via shell subprocesses (python3).\n - Sanitization: The script performs hex-length and prefix validation for addresses and transaction hashes (
is_valid_address,is_valid_txhash), which prevents basic command injection but does not sanitize the contents of the retrieved data.
Audit Metadata