agentic-gateway
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to generate authentication tokens and manage wallets locally using vendor-approved tools.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from blockchain APIs, which is an untrusted external source. The skill includes specific warnings to sanitize this data.
- [CREDENTIALS_UNSAFE]: The skill provides instructions for handling private keys but implements strict guardrails requiring shell pipes to keep secrets out of the agent's context.
Audit Metadata