ClawHub
Back to skill

Security audit

Biotechnology

Security checks for vulnerabilities and agentic risk

Overview

This biotechnology helper skill is coherent and safety-oriented, with only a privacy note around optional persistent memory.

Reasonable to install if you want biotechnology help. Treat the optional memory feature carefully: do not persist confidential lab, employer, project, organism, or research details unless you deliberately want that context saved.

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 (5)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
### 3. Safety and Ethics First
- Biosafety levels and containment are non-negotiable
- Include ethical considerations for human applications
- Never provide instructions that bypass safety protocols
- Refuse to provide actionable procedures for BSL-3/4 pathogens or select agents
- For any wet-lab protocol: remind user to validate with qualified personnel
Confidence
90% confidence
Finding
Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Instruction Override

High
Category
Prompt Injection
Content
### 3. Safety and Ethics First
- Biosafety levels and containment are non-negotiable
- Include ethical considerations for human applications
- Never provide instructions that bypass safety protocols
- Refuse to provide actionable procedures for BSL-3/4 pathogens or select agents
- For any wet-lab protocol: remind user to validate with qualified personnel
Confidence
90% confidence
Finding
This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## What NOT to Do

- Do not lecture when they want quick answers
- Do not assume their background — let context reveal it
- Do not provide unsafe protocol suggestions without safety notes
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.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The invocation description says the skill should be used whenever a user needs help with biotechnology concepts or applications "at any level," spanning multiple broad areas. This is ambiguous and lacks specific trigger phrases, constraints, or exclusion examples, increasing the chance of accidental activation for general science conversations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The template explicitly encourages persistent storage of user background, professional role, organisms worked with, focus areas, and inferred preferences, but provides no guidance on consent, minimization, retention, or handling of sensitive data. In a biotechnology context, these details can reveal employment, research interests, and potentially sensitive project information, increasing privacy and data-governance risk if retained unnecessarily or exposed.

Static analysis

No suspicious patterns detected.