skills/plurigrid/asi/acp-commons/Gen Agent Trust Hub

acp-commons

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a static knowledge base and reference guide for ACP and OCapN-grounded actors without implementing any active capabilities.
  • [COMMAND_EXECUTION]: There are no shell commands or scripts present in the skill. References to binary locations (e.g., zig-out/bin/zoad) are descriptive only.
  • [DATA_EXFILTRATION]: The skill references local file paths for various implementations, including paths specific to a developer environment (e.g., /Users/bob/i/zoad/ and ~/.jetbrains/acp.json). These are used for architectural mapping and do not involve any unauthorized data access or network transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 12:17 AM
Security Audit — agent-trust-hub — acp-commons