ClawHub
Back to skill

Security audit

Videntic AI Visibility

Security checks for vulnerabilities and agentic risk

Overview

The skill provides scoped Videntic analytics access and requires user authorization for changes, with no hidden execution or unrelated access.

Choose only the Workspace and action permissions you need; prefer read-only access for analytics. Before requesting changes, review their effects on usage allowances and tracking. Complete OAuth through your client and never paste credentials into chat.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
## Connect

Use an existing Videntic MCP connection. If unavailable, direct the user to add the remote URL in their client's MCP settings and complete OAuth sign-in. The user chooses the permitted Workspace and actions. This skill does not install a connector or grant access. The MCP does not accept Videntic Public API keys; do not ask users to paste credentials into chat.

Discover the connected server's tools and schemas before calling them. Respect the fields and capabilities exposed by that connection; names below identify the intended tools even when a client adds a prefix.