skills/bbengamin/skills/outreach-gate/Gen Agent Trust Hub

outreach-gate

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes vendor-provided tools including the paperclipai CLI and the @bbengamin/paperclip-mcp-server. These are legitimate dependencies for the Paperclip orchestration platform.
  • [COMMAND_EXECUTION]: Executes shell commands via the paperclipai CLI and curl to manage the Paperclip environment and verify connectivity.
  • [DATA_EXFILTRATION]: Orchestrates data transfer between the Twenty CRM and integrated sales automation services (Grinfi, Instantly, Apollo). These operations are consistent with the skill's stated purpose of outbound campaign management.
  • [SAFE]: Evaluated the indirect prompt injection surface:
  • Ingestion points: Reads resolved leads from Twenty CRM (SKILL.md).
  • Boundary markers: Includes explicit instructions to honor suppression, dedup, and consent rules; prohibits moving suppressed persons forward.
  • Capability inventory: Can execute CLI commands, perform CRM writes via engine skills, and manage blocklists in external tools (Grinfi, Instantly).
  • Sanitization: Delegates all data writes to the twenty-engine-sync skill, which implements additive and dry-run-first policies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 08:27 PM
Security Audit — agent-trust-hub — outreach-gate