ClawHub
Back to skill

Security audit

Clear Task

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed requirements-clarification workflow that requires confirmation before execution and contains no executable code or hidden external behavior.

Install only if you want an agent workflow that pauses to clarify requirements before acting. Be aware that after you explicitly confirm the requirement handoff, it may proceed to perform the confirmed task with the tools normally available to your agent, while still asking before credentials, paid services, network actions, destructive operations, or unexpectedly broad changes.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 133)May include surrounding context.

md
- the task requires credentials, paid services, network actions, or destructive operations,
- the user explicitly asked only for analysis, planning, or the internal handoff package.

## Output Rules

- Preserve traceability from user input, Stage1, Stage2, and expert recommendations.
- Separate `confirmed_facts`, `accepted_defaults`, `assumptions`, and `expert_recommendations`.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hard-codes Chinese-only confirmation labels and examples for the required approval gate, which can cause users operating in other languages to misunderstand the gating step or fail to give recognizable consent. In a workflow that blocks or authorizes downstream execution based on exact confirmation semantics, this creates a safety and usability weakness that can lead to accidental progression or repeated ambiguity.

Content

No source excerpt is available for this finding.