outreach

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @membranehq/cli package from the npm registry, which is the official tool provided by the vendor.
  • [COMMAND_EXECUTION]: Executes shell commands using the membrane CLI to perform authentication, discover available actions, and manage Outreach integration workflows.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it retrieves and processes records from Outreach (such as prospect details, account information, or email templates) that could contain malicious instructions.
  • Ingestion points: External data fields from Outreach objects retrieved via the Membrane CLI.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted data from the agent's instructions.
  • Capability inventory: Shell command execution, dynamic action creation, and network operations through the vendor's platform.
  • Sanitization: The instructions do not specify any validation or sanitization of content ingested from external Outreach records.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:38 AM