clanker

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill's token deployment interface accepts arbitrary user-supplied strings for token names, symbols, and descriptions, creating a surface for indirect prompt injection.\n
  • Ingestion points: Parameters name, symbol, and metadata.description in the deploy() configuration examples within SKILL.md and references/deployment.md.\n
  • Boundary markers: Code snippets do not demonstrate the use of delimiters or instructions to ignore embedded commands within user-provided data.\n
  • Capability inventory: The skill enables the agent to execute blockchain transactions for contract deployment, airdrops, and fee claims.\n
  • Sanitization: No explicit sanitization or validation of metadata content is present in the instructional examples.\n- [EXTERNAL_DOWNLOADS]: The documentation references and encourages the installation of the clanker-sdk and viem packages from NPM, which is a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:42 PM