ClawHub
Back to skill

Security audit

Scientific Thinking — Biology & Life Science

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only biology reasoning skill that helps calibrate scientific claims and does not request unusual access or execution authority.

Installers should understand that this skill may be invoked for many biology-related questions and will tend to produce structured, cautious research-style answers. It does not add execution privileges, but users should still rely on normal platform safeguards for clinical, biosafety-sensitive, or procedural laboratory advice.

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 162)May include surrounding context.

md
**Do not:**
- Call a gene a driver based on expression correlation alone
- Treat a mouse phenotype as established human biology without caveats
- Use confident mechanistic language when only correlative data exist
- Ignore alternative explanations (redundancy, compensation, off-target, composition bias)
- Treat enrichment scores as evidence of pathway activity without noting the limitation

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

该行写明“任何存在过度解读机制风险的生物学问题”，触发范围非常宽泛，未说明具体调用条件、边界或排除情形。作为 markdown 技能说明，这种描述容易导致在大量普通生物学讨论中被不必要地激活。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill's trigger description is extremely broad, covering essentially any biology or life-science reasoning task. In an agentic system, that can cause over-invocation, priority hijacking, or inappropriate routing of general scientific or medical questions into this skill, expanding its authority beyond a narrowly scoped purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

该文件主体内容为中文，虽然提供了英文链接，但文档本身没有说明应依据用户语言偏好选择输出语言。按照自然语言策略要求，技能不应在缺乏用户明确选择时默认强制特定语言或地区表达。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.