core-actionbook

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured documentation and configuration for MCP tools (search_actions, get_action_by_id) used to retrieve element selectors for browser automation workflows.- [SAFE]: No obfuscation, data exfiltration, or unauthorized command execution patterns were detected.- [SAFE]: The skill includes security-conscious configuration in the YAML frontmatter, specifically setting user-invocable: false and disable-model-invocation: true, which limits the execution scope and reduces the potential attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 05:48 PM
Security Audit — agent-trust-hub — core-actionbook