ClawHub
Back to skill

Security audit

Desk Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed desk-research workflow that guides public-source research and report structure without code execution, persistence, credential handling, or hidden data movement.

Install this if you want a structured public-source research workflow. Be aware that some reference guidance is in Chinese, so set your preferred output language when using it if that matters.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.

md
- For each promising case, collect at least 3 website evidence snippets (feature/pricing/use-flow)
- Add at least 1 metric anchor from trusted dataset (revenue/MRR/growth)
- Include at least 1 risk point and 1 falsification condition
- Do not submit if any case is only descriptive without judgment

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction to "Execute this workflow for any desk-research request" does not define clear boundaries for what qualifies as a desk-research request. Combined with the broad description in L003, this could cause unintended invocation for general questions, summaries, or analysis tasks that overlap with ordinary user requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The title and body of the document are written in Chinese, which imposes a single language on users without any opt-in, alternative language option, or stated regional justification. This matches the policy category for language/locale constraints expressed in natural language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The checklist line embeds a required summary format in Chinese characters ("做什么/用户是谁/商业模式/为什么付费") within an otherwise English document. This can be read as forcing a specific language or locale convention without user opt-in or documented regional justification, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.