quicknode-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data fetched from external blockchain sources which could contain malicious instructions intended to influence agent behavior.
- Ingestion points: Blockchain data retrieved via API methods
qn_getWalletTokenBalance,qn_fetchNFTs, andqn_getWalletTokenTransactionsinSKILL.md. - Boundary markers: No delimiters or explicit instructions are provided to the agent to treat external blockchain data as untrusted content.
- Capability inventory: The skill is configured with access to potentially sensitive tools including
Bash(npm:*),Write, andEditas defined in the YAML frontmatter. - Sanitization: There is no evidence of string validation or sanitization for the data retrieved from the QuickNode API before it is utilized by the agent.
- [EXTERNAL_DOWNLOADS]: The skill depends on the
@quicknode/sdkandethersNode.js packages. These are well-known, industry-standard libraries for blockchain development and represent standard functionality for this skill's use case.
Audit Metadata