Akashic Doc Analyzer

Security checks across malware telemetry and agentic risk

Overview

This is a coherent document-analysis skill, with the main caution that user-selected documents are processed through an external Akashic MCP service.

Install only if you trust the Akashic MCP provider for the documents you plan to analyze. Avoid sending confidential, regulated, or highly personal files unless you have confirmed the provider's handling, retention, and access controls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are broad enough to match many ordinary document-related requests, which can cause the skill to activate unexpectedly and intercept workflows that users may have intended for safer or more specific built-in capabilities. Because this skill can process file paths and route content through external MCP tools, overbroad activation increases the risk of unintended document access, data exposure, or tool invocation without clear user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal