ClawHub
Back to skill

Security audit

goudantest

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only code review skill whose behavior matches its stated purpose and does not request unusual access or persistence.

Install this if you want structured code review help. Be aware that it may activate for a wide range of code review and code analysis requests, so users who prefer narrower routing may want a more specialized review 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description uses very broad activation conditions such as general code reviews, security audits, performance reviews, and detailed code analysis across many languages. This can cause the skill to be invoked for a wide range of common developer requests, increasing the chance of unintended routing, context mixing, or activation in situations where a narrower skill would be safer or more appropriate.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · TEMPLATES.md (reported line 414)May include surrounding context.

md
### DON'T:
- Make vague comments ("this looks wrong")
- Nitpick on style if linter handles it
- Assume intent without asking
- Use harsh or dismissive language
- Focus only on problems without solutions

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file includes bilingual Chinese text in headings, such as '逻辑正确性', without stating that the skill is intended for bilingual users or offering a language preference. Under the policy, forcing or assuming a language/locale without user opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.