discover-artblocks-projects
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious patterns, suspicious network requests, or unauthorized data access were identified. The tools focus on querying public blockchain and platform data related to Art Blocks.
- [NO_CODE]: The skill consists entirely of documentation and tool specifications in a Markdown file. No scripts, binaries, or other executable files are included in the skill package.
- [PROMPT_INJECTION]: The skill defines tools that ingest untrusted data from the Art Blocks platform, creating a surface for indirect prompt injection. * Ingestion points: Tools such as get_project and discover_projects return untruncated project descriptions and metadata. * Boundary markers: No delimiters or instructions to ignore embedded prompts are mentioned in the tool definitions. * Capability inventory: The tools provided are limited to read-only operations for platform discovery, though they are designed to work alongside transaction-building tools. * Sanitization: No explicit sanitization or filtering of platform-provided content is described.
Audit Metadata