ClawHub
Back to skill

Security audit

STORM Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-impact research-structuring template and does not request code execution, credentials, broad data access, or persistence.

Install this if you want a structured pre-writing research workflow. Treat its perspective output as planning material, not verified facts, and use separate source-backed research before relying on claims, especially for high-stakes topics.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broadly phrased around topics, trends, articles, product questions, and learning areas without clear activation boundaries or eligibility checks. In an agent ecosystem, this can cause over-triggering on loosely related prompts, leading the agent to invoke the skill in inappropriate contexts and potentially propagate unverified research scaffolding into sensitive or high-stakes workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The description includes Chinese text ('关注作者') embedded in otherwise English skill metadata, which introduces a language-specific element without indicating that the user can choose their preferred language. This can be a natural-language policy concern when a skill presents locale-specific content without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language content is entirely specified in Chinese, which implicitly constrains the skill's language/locale without offering the user a choice. The file does not document that this is a region-specific or language-specific skill, so this appears to be an undocumented locale restriction.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest summary, keywords, and user needs are broad enough to match many generic research or writing-prep requests, which can cause the skill to trigger outside narrowly intended contexts. Overbroad activation is dangerous because it increases the chance of unintended invocation, exposing users to unreviewed skill behavior or prompting the agent to prioritize this skill when a simpler, safer default response would suffice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.