ClawHub
Back to skill

Security audit

Cca

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese CCA study-guide skill with no harmful instructions, but it asks for broad Read and Bash tool access that its tutoring purpose does not need.

Review this before installing because a simple CCA tutoring skill should not need Bash or broad file-reading authority. Prefer a version with those tool permissions removed or tightly scoped; the Chinese-only content is otherwise transparent and expected from the artifact.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description and instructional content are entirely in Chinese and position the agent as a Chinese-language study tutor, but they do not state that language is optional or user-selectable. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.