Akashic Deep Researcher

• Outcome: Pass
• Latest audit: May 29, 2026, 8:29 PM
• Version:
  1.0.0

Overview

This is an instruction-only research skill that clearly uses a disclosed Akashic web/deep-research service and does not request local access, persistence, or privileged actions.

Install this only if you are comfortable sending research prompts to the configured Akashic MCP service. Avoid entering confidential, personal, or regulated information unless that service is approved for that data, and be aware the broad triggers may activate it for general research-like phrasing.

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: 92% confidence
• Finding: The trigger list includes broad everyday phrases such as "look into," "find out about," and "study," which are likely to match many ordinary user requests outside the intended scope. This can cause unintended activation of the skill, leading the agent to invoke web/deep research tools when the user did not explicitly request them, increasing data exposure, unnecessary external calls, and prompt-routing risk.

VirusTotal

57/57 vendors flagged this skill as clean.