Back to skill

Security audit

Enhanced Search

Security checks for vulnerabilities and agentic risk

Overview

This search-assistant skill is purpose-aligned and contains no executable code, but users should be aware that context-aware web searches and optional search-pattern tracking can expose query context.

Before installing, use this skill only with searches you are comfortable sending through web search. Avoid asking it to include sensitive prior-chat details in optimized queries, and review or disable any future self-improving-agent integration that records search patterns.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly performs web searches and uses conversation context to optimize queries, but the documentation does not warn users that their queries and possibly prior chat context may be sent to external search services. This creates a privacy and data-handling risk because users may unknowingly disclose sensitive information to third parties during normal use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The integration note says the skill can work with a self-improving agent to record search patterns and optimization effectiveness, which is telemetry-like behavior. Without an explicit warning, consent mechanism, and retention controls, this can enable silent collection of behavioral data about user interests and activity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file presents all user-facing instructions and examples in Chinese, which effectively forces a specific language for use and maintenance without opt-in or explanation. The policy allows locale constraints only when they are user-selectable or clearly justified as region-specific, neither of which is stated here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.