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/agentwallet is explicitly listed as a requirement in SKILL.md and checked in scripts/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.sh runs the emblemai CLI 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, and nansen_defi_portfolio described in SKILL.md.
  • Boundary markers: None present in the instructions to separate external data from agent commands.
  • Capability inventory: Shell command execution via the emblemai CLI in scripts/portfolio-report.sh.
  • Sanitization: No explicit sanitization or filtering of the fetched blockchain data is defined in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 03:36 PM
Security Audit — agent-trust-hub — emblem-portfolio-tracker