query-artblocks-data
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation and query patterns for Art Blocks data. No malicious commands, obfuscation, or attempts to bypass agent security filters were identified.
- [DATA_EXPOSURE]: Analysis confirms the skill interacts only with public blockchain data (Ethereum, Arbitrum, Base) and an internal platform context resource (artblocks://about). There is no access to sensitive local directories, SSH keys, or environment secrets.
- [EXTERNAL_DOWNLOADS]: The skill references a Model Context Protocol toolset (artblocks-mcp) intended for the agent's environment. It does not perform unauthorized downloads, remote script execution, or package installations from unknown sources.
- [PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection risks associated with processing data from the blockchain. The risk is considered negligible as the tools are focused on data retrieval and lack capability chains that could lead to privilege escalation or unauthorized system access.
Audit Metadata