Baseline-RAG

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.2

Overview

This is a disclosed fact-checking skill that may trigger too broadly, but it does not show hidden code, credential access, persistence, or destructive behavior.

Install only if you are comfortable with a fact-checking skill that can activate on common verification wording. Use it for non-sensitive claims, treat its confidence score as a rough heuristic, and review the external Cross-Validate/endpoint service before following upsell links or sending private information.

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 (3)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger list includes generic phrases like "verify," "fact-check," and especially "confirm," which are common in normal conversation and can cause the skill to activate unintentionally. In a fact-checking skill, overbroad activation can hijack unrelated requests, alter routing behavior, and expose users to unwanted confidence-scoring or upsell flows even when they did not intend to invoke this capability.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrases are overly broad for a general-purpose fact-checking skill and include common language such as "verify," "is this true," and "confirm." In an agent environment, this can cause the skill to activate unintentionally in many ordinary conversations, creating scope creep, unexpected web access, and opportunities for prompt-routing abuse or user confusion.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger phrases are broad, natural-language expressions such as 'verify', 'fact-check', and 'is this true', which are likely to appear in normal conversation and can cause unintended skill invocation. This creates a prompt-routing or skill-selection risk where the agent may invoke this external verification skill when the user did not explicitly intend to use it, potentially affecting privacy, cost, or workflow integrity.

VirusTotal

65/65 vendors flagged this skill as clean.