Back to skill

Security audit

Tech Service Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent, non-executable assistant for collecting and querying public technology-service institution information, with only minor usability cautions.

Installers should understand that the skill is meant for public-source collection and reporting about technology-service institutions. Review its use of broad Chinese trigger terms if accidental activation would be disruptive, and prefer user-directed collection or updates when maintaining any SQLite state database.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger keywords are very broad domain terms such as '科技服务', '孵化器', and '专精特新', which can plausibly appear in many ordinary conversations. That increases the chance of unintended skill activation, causing the agent to inject specialized collection/query behavior or policy constraints into unrelated user requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Mandating Markdown table output for all query results imposes a formatting policy regardless of user preference or accessibility needs. While not a direct security exploit, it can reduce user control and create prompt-routing or policy-conflict issues when a different format is required.

Content

No source excerpt is available for this finding.