ClawHub
Back to skill

Security audit

Grant Thinking CN Biology

Security checks for vulnerabilities and agentic risk

Overview

This is a region-specific grant-reasoning skill with no executable code or tool permissions, though users should only use it when they want China-focused biology grant advice.

Install this if you want biology grant feedback in a Chinese funding context such as NSFC or MOST. For other countries or general grant writing, avoid relying on it by default or ask your agent to confirm the target funding system before using this skill.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The README describes the skill as oriented to Chinese grant contexts and presents the documentation entirely in Chinese, but it does not explicitly state that this locale/language restriction is optional or user-selectable. Under the policy for natural-language violations, forcing a specific language or locale without opt-in can be a concern unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill is explicitly framed around the Chinese funding context across its description and capabilities, but there is no visible requirement to obtain user opt-in before applying that lens. If invoked in a broader grant-writing context, it may steer outputs toward a specific national regime, misalign advice, and produce biased or unsuitable recommendations for users in other jurisdictions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation without any stated trigger constraints, exclusions, or user-confirmation guardrails. That creates a real risk of inappropriate auto-selection in conversations that mention grants, biology, or evaluation, causing the agent to inject China-specific funding assumptions without an explicit user request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The README repeatedly frames the skill as reasoning for China's funding context and Chinese grant systems, which is a locale-specific constraint. While the domain focus is clear, the file does not explicitly state that the locale specialization is optional or user-selected, which can qualify as a natural-language locale policy issue under the stated rule.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill is described as a reasoning aid for evaluating Chinese biology grant ideas, but the README embeds remotely hosted payment QR-code images for donations. Loading those images causes external network access that is not justified by the stated analytical purpose of the skill itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The instructions repeatedly constrain the assistant to operate in the Chinese funding context and to think like a reviewer familiar with Chinese grant expectations. This is a locale-specific policy choice presented as mandatory behavior, but the file does not offer the user an explicit language/locale choice or opt-in mechanism.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
- and appropriately scoped for the target project level.

This skill is designed for Chinese biology funding contexts such as NSFC, MOST-type programs, and similar grant systems.
It is not limited to youth grants.
It should remain adaptable across project levels.

## Core mission

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The heading 'Grant Thinking CN Biology Checklist' embeds a 'CN' locale/language constraint, but the file does not explain whether this is optional, user-selected, or justified by a region-specific use case. This can indicate a natural-language policy issue if the skill is implicitly scoped to a specific language or locale without explicit opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.