ClawHub
Back to skill

Security audit

new-term-radar

Security checks for vulnerabilities and agentic risk

Overview

The skill’s disclosed research workflow fits its purpose and requires user approval before paid API calls.

Review the configured sources and approve estimated costs before running. Research queries go to external providers, and snapshots remain locally. Installation also requires trusting the pinned external Python package, whose implementation is outside the supplied artifact.

A.I.G

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

SkillSpector

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
86% confidence
Finding

The executable matches the declared tool, but the supplied invocation has a materially different apparent task: pains analysis for one fixed query. The chunk does not demonstrate recent-name discovery, keyword-volume and trend comparisons, or prioritization decisions. The internal behavior of the pains subcommand is not supplied, so its exact data sources and outputs cannot be verified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.