emblem-memecoin-scout

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @emblemvault/agentwallet NPM package to provide the emblemai command-line interface.- [COMMAND_EXECUTION]: The skill makes extensive use of shell commands via the emblemai CLI to perform blockchain queries and token analysis, as seen in the usage examples and the scripts/memecoin-scan.sh helper script.- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external sources, such as Pump.fun, Clanker, and Rugcheck, which may contain attacker-controlled content embedded in token metadata or holder information.
  • Ingestion points: Data fetched through tools like getPumpFunTokens, baseFindClankerTokens, and rugcheck referenced in SKILL.md.
  • Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the external data it processes.
  • Capability inventory: The skill utilizes the emblemai CLI to execute various tasks, which involves shell execution (referenced in scripts/memecoin-scan.sh).
  • Sanitization: There is no evidence of sanitization or filtering of the external token data before it is presented to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:48 PM
Security Audit — agent-trust-hub — emblem-memecoin-scout