emblemai-crypto-wallet
Warn
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@emblemvault/agentwalletpackage via NPM and fetch additional code and instructions from theEmblemCompany/Agent-skillsGitHub repository. - [COMMAND_EXECUTION]: The setup process involves running
npm installandnpx skills add, which execute third-party code and modify the execution environment. - [DATA_EXFILTRATION]: The skill performs network operations to
api.agenthustle.aito retrieve balance and portfolio data and to execute transactions. This involves sending wallet addresses and potentially sensitive transaction details to an external service. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from blockchain APIs that could contain malicious instructions.
- Ingestion points: Data retrieved from
api.agenthustle.ai(specifically/portfolioand/tokenendpoints) as described inSKILL.md. - Boundary markers: Absent; there are no instructions to the agent to ignore or delimit instructions found within the external data.
- Capability inventory: The skill possesses high-impact capabilities including token swaps (
POST /swap) and transfers (POST /transfer). - Sanitization: No sanitization or validation logic is mentioned for the data returned from external blockchain contracts or API endpoints.
Audit Metadata