emblem-memecoin-scout

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the global installation of the "@emblemvault/agentwallet" Node.js package, which provides the necessary "emblemai" CLI for blockchain interactions.
  • [COMMAND_EXECUTION]: The provided "scripts/memecoin-scan.sh" script executes the "emblemai" command-line tool with hardcoded arguments to perform automated scans of various token launch platforms.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted content from external decentralized finance (DeFi) APIs and token launchpads.
  • Ingestion points: Data is retrieved from external sources including Pump.fun, LaunchLab, Clanker, and Hedera via tools like "getPumpFunTokens" and "baseFindClankerTokens" as documented in "SKILL.md".
  • Boundary markers: The instructions do not define specific delimiters or security wrappers to isolate external token metadata from agent instructions.
  • Capability inventory: The skill possesses the ability to execute shell commands via the "emblemai" CLI tool, which is used to process the retrieved data.
  • Sanitization: No explicit sanitization, validation, or escaping of fetched token data is described before the information is passed back into the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 11:00 AM