Docsbot Ai

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.4

Overview

This is a coherent DocsBot AI integration, but it gives an agent broad authenticated power to delete or change DocsBot data without clear confirmation guardrails.

Install only if you are comfortable granting Membrane-mediated access to your DocsBot account. Use the least-privileged DocsBot account or a test workspace where possible, prefer listed read-only actions before mutations, and require the agent to show the exact bot/source/question/conversation ID and request body before any create, update, delete, or non-GET proxy request.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill advertises destructive capabilities such as deleting conversations, questions, sources, and bots without any caution, confirmation guidance, or human-review requirement. In an agent setting, this increases the chance of accidental or unauthorized destructive operations being executed from ambiguous user prompts or misinterpretation.

VirusTotal

65/65 vendors flagged this skill as clean.