ClawHub
Back to skill

Security audit

Scientific Thinking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent scientific-reasoning guide with no code execution, credential access, or hidden persistence.

Install this if you want research and evidence-evaluation answers to be more structured. Be aware that implicit invocation is enabled for compatible agents, so it may shape scientific or research-adjacent answers automatically; disable or avoid it if you only want explicit activation.

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 allows implicit invocation with no trigger phrases, scope limits, or activation constraints, which can cause it to be invoked in situations the user did not clearly intend. Because this skill shapes reasoning and interpretation of scientific evidence, unintended activation could subtly steer analysis, framing, or conclusions without explicit user awareness, increasing the risk of overreach or misuse in adjacent domains.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

该文件本身以中文呈现，并在开头仅提供一个英文 README 链接，没有说明技能运行时语言可由用户选择。按规则，若技能或文档对语言有强制性而缺少明确的用户选择或 opt-in，可能属于自然语言策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.