campaign-impact-analyzer

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill leverages Model Context Protocol (MCP) integrations for La Growth Machine and HubSpot. It uses specialized tools (e.g., list_campaigns, get_campaign_stats) to access data, which is the standard and secure method for agent-service interaction. \n- [SAFE]: Step 4 defines a clear data normalization workflow where external data (from MCPs or user pastes) is mapped to a strict internal schema. This acts as a security boundary by ensuring the agent only processes expected data fields, which mitigates risks associated with indirect prompt injection from untrusted external datasets. \n- [SAFE]: The skill provides evidence of input sanitization in Step 4, such as normalizing emails (lowercase and alias stripping) before performing join operations. \n- [EXTERNAL_DOWNLOADS]: The installation instructions suggest using 'npx skills add' from Vercel Labs to download the skill from the author's official GitHub repository. This is a recognized installation pattern from a well-known service. \n- [SAFE]: The skill checks for the presence of local sibling skills using standard file globbing to ensure modular functionality, without attempting privilege escalation or persistent access.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 02:55 PM
Security Audit — agent-trust-hub — campaign-impact-analyzer