ClawHub
Back to skill

Security audit

Deep Research Suite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown research workflow that asks the agent to search public sources, synthesize findings, and save reports, with no executable code or hidden behavior found.

Install only if you want an agent to perform multi-source online research and save resulting reports locally. Avoid using it for confidential topics unless you are comfortable with generated research notes being written to memory/research/ or long-term memory integrations.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises a very broad, one-command research capability without clear trigger constraints or scope boundaries, which can cause an agent to activate in overly general contexts and perform unintended multi-step actions. In this skill, that risk is amplified because activation can lead to external searching, content aggregation, and local file writes, increasing the chance of unnecessary data handling or surprise side effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill behavior includes saving generated research reports to local files, but the description near the functionality overview does not clearly warn users about this side effect before execution. That can lead to unanticipated persistence of potentially sensitive queries, collected source material, or synthesized outputs on disk, especially in shared or monitored environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.