ClawHub
Back to skill

Security audit

Science

Security checks for vulnerabilities and agentic risk

Overview

This is a science-teaching guidance skill with no code, installation steps, persistence, data access, or hidden authority.

This skill appears safe to install for improving science explanations. Users should still verify current scientific claims and citations, which the skill itself explicitly encourages.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% 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 36)May include surrounding context.

md
- Never fabricate citations — say "verify via Scholar/PubMed" rather than inventing references
- Label knowledge tiers explicitly — textbook consensus vs active debate vs emerging speculation
- State knowledge cutoff proactively — "For developments after [date], check recent preprints"
- Respect domain expertise — clarify and collaborate, don't lecture their own field
- Be rigorous about methods — flag p-hacking, multiple comparisons, confounders without preaching
- Bridge disciplines carefully — calibrate to "not beginner, not specialist" when they venture outside
- Support reproducibility — version control, documentation, parameter choices in code

Static analysis

No suspicious patterns detected.