emblem-portfolio-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a global Node.js package provided by the vendor to perform its operations.
- Evidence:
npm install -g @emblemvault/agentwalletis explicitly listed as a requirement inSKILL.mdand checked inscripts/portfolio-report.sh. - [COMMAND_EXECUTION]: The skill includes documentation and a helper script that execute shell commands to interact with the blockchain data aggregator.
- Evidence:
scripts/portfolio-report.shruns theemblemaiCLI tool with various flags to retrieve wallet addresses, balances, and trade positions. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external blockchains and DeFi protocols, which constitutes an attack surface for instructions embedded in transaction data or token metadata.
- Ingestion points: Data returned from tools such as
solanaBalances,ethGetBalances, andnansen_defi_portfoliodescribed inSKILL.md. - Boundary markers: None present in the instructions to separate external data from agent commands.
- Capability inventory: Shell command execution via the
emblemaiCLI inscripts/portfolio-report.sh. - Sanitization: No explicit sanitization or filtering of the fetched blockchain data is defined in the skill logic.
Audit Metadata