Back to skill

Security audit

Akashic Knowledge Base

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent knowledge-search purpose, but its broad everyday triggers and external search/AI workflow create a real risk of unintentionally sending sensitive questions or internal context outside the knowledge base.

Review before installing. This skill is not showing malicious behavior, but users should treat it as a Review item because ordinary questions may invoke it and because internal or sensitive questions could be routed into external search or AI synthesis. Prefer narrower triggers and require explicit user approval before sending proprietary content to web search or external model providers.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

The trigger 'search for' is close to a built-in 'search' command and may shadow or intercept expected platform behavior. In this skill, that ambiguity is more dangerous because invocation can lead to external searches and AI synthesis, increasing the chance of unintended data disclosure or tool use.

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
86% confidence
Finding

The trigger 'find information' overlaps with a common built-in 'find' style command, making accidental or ambiguous invocation plausible. Given the skill's ability to query internal data and external services, this confusion can cause unintended retrieval or transmission of user requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrases are generic everyday language such as 'what is' and 'tell me about', which can cause the skill to activate unintentionally during normal conversation. Because this skill can invoke external search and AI tools, accidental activation may expose user queries to third-party services or cause unintended tool execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly performs external web search via SerpApi and Tavily, but it does not warn users that their queries may be transmitted to third-party providers. This creates a privacy and data-handling risk, especially because the workflow encourages using web search and combining it with internal knowledge retrieval.

Content

No source excerpt is available for this finding.