skills/sales-skills/sales/sales-vwo/Gen Agent Trust Hub

sales-vwo

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes a persistent file, references/learnings.md, to store 'accumulated platform knowledge' which the agent reads at the start of every session. This creates a surface for Indirect Prompt Injection (Category 8).
  • Ingestion points: The file references/learnings.md is read during Step 1 to gather context.
  • Boundary markers: None are present; content is treated as authoritative knowledge.
  • Capability inventory: The agent follows instructions retrieved from the learning file to provide answers and guide users.
  • Sanitization: The skill lacks sanitization, instructing the agent to append new findings directly to the file.
  • [EXTERNAL_DOWNLOADS]: The skill recommends several official SDKs and tools (e.g., vwo-fme-node-sdk, vwo-fme-python-sdk) hosted on the Wingify GitHub organization and public registries. These are official resources provided by the platform vendor.
  • [COMMAND_EXECUTION]: Documentation within the skill includes commands for users to install SDKs and related skills from the same author (sales-skills). These are provided as legitimate setup instructions for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 06:35 PM