Edvisage Trust Checker

• Outcome: Pass
• Latest audit: May 29, 2026, 8:33 PM
• Version:
  1.0.2

Overview

This is a documentation-only trust-checking protocol with disclosed memory logging and no scripts, network calls, hidden install behavior, or destructive actions.

Reasonable to install if you want a cautious trust-checking checklist. Review the memory entries it writes, and verify the publisher or repository if you plan to rely on its security claims.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (1)

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: The trigger condition includes a subjective clause: taking action that merely 'feels unusual given your normal operating context.' In a security protocol this can cause over-triggering, inconsistent enforcement, or unintended refusal loops because the criterion is not objectively testable and may be interpreted differently across agents or contexts.

VirusTotal

65/65 vendors flagged this skill as clean.