salespype

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to install and use the @membranehq/cli utility to manage authentication and execute integration logic. This is a vendor-owned resource used for its intended purpose of connecting to the Salespype service.\n- [PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Salespype, which presents a surface for indirect prompt injection.\n
  • Ingestion points: Data is retrieved from the Salespype API through commands like membrane action run and membrane request as documented in SKILL.md.\n
  • Boundary markers: The instructions lack specific delimiters or instructions to treat external data as untrusted content.\n
  • Capability inventory: The skill enables the agent to perform write operations and arbitrary API requests via membrane action run and membrane request.\n
  • Sanitization: There are no documented measures for sanitizing or validating content retrieved from the CRM before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 12:07 AM
Security Audit — agent-trust-hub — salespype