clanker
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and encourages the installation of external Node.js packages, including
clanker-sdk,viem, and@openzeppelin/merkle-tree, which are required for its primary functionality.\n- [CREDENTIALS_UNSAFE]: The documentation provides instructions for setting up an environment variable for a blockchainPRIVATE_KEY. This involves the handling of highly sensitive credentials that could result in total loss of funds if compromised.\n- [COMMAND_EXECUTION]: The skill facilitates high-impact operations by executing blockchain transactions, such as token deployment, setting up vesting vaults, and claiming trading rewards.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user data without explicit sanitization.\n - Ingestion points: User-provided strings for token
name,symbol, andmetadata.descriptionare processed and written to the blockchain as part of the deployment configuration.\n - Boundary markers: The provided code snippets do not include delimiters or safety instructions to distinguish user-provided metadata from core logic.\n
- Capability inventory: The skill possesses the capability to perform network requests (via RPC providers) and execute state-changing transactions on public ledgers.\n
- Sanitization: No evidence of input validation, escaping, or schema enforcement for user-provided metadata strings is present in the analyzed files.
Audit Metadata