local-competitor-scan

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns, such as prompt injection, obfuscation, or privilege escalation, were detected. The skill operates as a structured research assistant.
  • [EXTERNAL_DOWNLOADS]: The skill references and requires the installation of external plugins (unifapi-agent/agents and unifapi@unifapi) to access the UnifAPI Model Context Protocol (MCP) server. These resources are provided by the skill's author and are used for legitimate API access via OAuth.
  • [DATA_EXFILTRATION]: The skill instructions include steps to read local project context from files like .agents/product-marketing.md. This is used to automatically identify target queries and business locations for the SEO analysis within the agent's operating environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 04:06 PM
Security Audit — agent-trust-hub — local-competitor-scan