icp-persona-builder
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely instruction-based (prompt-driven) and does not include any executable scripts, binaries, or configuration files that run code. Behavior is restricted to agent-executed web searching and fetching.
- [SAFE]: Analysis of the instructions confirms they are focused on legitimate market research tasks. There are no attempts at prompt injection, data exfiltration, or obfuscation. The skill uses standard agent capabilities (WebSearch, WebFetch) to gather public information about companies and saves the resulting analysis locally as structured data (JSON/Markdown) for the user.
Audit Metadata