Back to skill

Security audit

new-term-radar

Security checks for vulnerabilities and agentic risk

Overview

The skill provides coherent AI keyword research with disclosed API costs, credential use, and user approval controls.

Review the external package before supplying API keys, choose the accounts and sites to research, and approve the estimated cost before each paid run. Queries go to the disclosed providers, and reports and snapshots remain locally. This review covers the skill instructions, not the downloaded executable.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
83% confidence
Finding

Although the executable matches the declared tool, the supplied invocation targets pains for a fixed topic, not the advertised signal-to-decision radar workflow. The chunk does not show recent-name discovery, search-volume sizing, trend evaluation, or prioritize/watch/skip decisions. The internal behavior of pains is not supplied, so the assessment is limited to the visible command and its apparent purpose.

Content

No source excerpt is available for this finding.