ClawHub
Back to skill

Security audit

Grant Thinking General

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent grant-proposal reasoning skill with no executable code, credentials access, background behavior, or hidden high-impact actions.

Reasonable to install if you want reviewer-aware grant proposal feedback. Be aware that implicit invocation may cause the skill's proposal-evaluation style to appear in nearby grant-writing conversations, and the README displays remote donation images if rendered by a client that loads external images.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file is in scope for vague-trigger review, and the description lists expansive conditions such as evaluating ideas, diagnosing logic, and preparing to write any section of a proposal without defining clear trigger boundaries. Because it does not provide specific trigger phrases, exclusions, or narrow context constraints, it may cause unintended invocation for general writing or brainstorming tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables implicit invocation with no stated trigger phrases, scope limits, or contextual constraints, so it may activate in loosely related conversations and influence outputs without clear user intent. Because this skill provides high-level reasoning and evaluation guidance, over-broad activation can cause unintended steering of proposal advice, leakage of internal orchestration behavior, or prompt-surface expansion for indirect prompt injection through nearby user content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The file includes a natural-language link to a Chinese README but does not explicitly state how language selection should work for users. Under the policy rule, locale or language handling should either be optional/opt-in or clearly justified; this line presents an alternate language without documenting the selection behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The skill is described as a grant-idea and proposal-reasoning aid, but the README includes externally hosted payment QR code images for author support. While this is documentation rather than execution code, it introduces a capability to fetch third-party resources that is not justified by the stated research-proposal assistance purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file is written as a Chinese-only skill description and does not state that the language is optional or limited to a China-specific use case. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation, even if an English document is linked separately.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.