ClawHub
Back to skill

Security audit

Deep Research

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent deep-research writing skill, with manageable cautions around broad activation wording and local draft-file creation.

Install this if you want long, sourced research reports. Before using it on sensitive topics, choose a workspace where intermediate draft files are acceptable, confirm filenames or output location, and use a simpler assistant path for quick summaries or ordinary explanations.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation criteria are very broad, covering generic requests such as 'detailed report' or 'thorough analysis,' which could cause the skill to trigger in many ordinary interactions. Over-broad triggering increases the chance that a high-autonomy workflow with web access, multilingual searching, and file-writing behaviors is invoked when a simpler or safer response path was intended.

Context-Inappropriate Capability

Medium
Confidence
87% confidence
Finding
The skill explicitly instructs the agent to create multiple draft files on disk as part of its normal workflow, even though the stated purpose is only to research and produce a report. Unnecessary file creation expands the skill's side effects, can leave sensitive intermediate content behind, and may overwrite or clutter the working environment without clear user consent or operational need.

Static analysis

No suspicious patterns detected.