ClawHub
Back to skill

Security audit

research

Security checks for vulnerabilities and agentic risk

Overview

This research skill is coherent and disclosed, but users should know it can launch multiple research agents and save reports/session data locally.

Install this if you want an agent-driven research workflow that may query external sources, launch parallel research agents, and save reports/session state in the workspace. Use care with sensitive research topics and review or delete saved docs/research output when needed.

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
  • 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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list includes broad terms like "research" and "synthesis," which are common across many benign conversations and can cause the skill to activate outside the user's intent. Because this skill orchestrates multi-agent work, external-source querying, and local session/report creation, unintended invocation can lead to unnecessary data collection, tool use, and file writes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to save a formatted report under docs/research/ and persist session state with mgr.save(session) without requiring prior user consent or clearly warning about local filesystem writes. In an agent environment, silent persistence can expose sensitive prompts, topics, or derived findings to disk and create unexpected side effects in the user's workspace.

Static analysis

No suspicious patterns detected.