ClawHub
Back to skill

Security audit

Certificates

Security checks for vulnerabilities and agentic risk

Overview

This is a small documentation-only skill for electronic certificate guidance, with some vague and overbroad wording but no executable behavior, persistence, or data access.

Installers should treat this as a general Chinese-language e-certificate guidance skill, not an authority to submit identity documents or use third-party services. For real ID, license, or qualification workflows, verify details through official government channels and avoid sharing sensitive documents unless the service is clearly official.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documentation substantially broadens scope from government certificate issuance/display and mutual recognition into generic tool comparison, performance metrics, cloud backup, plugin support, and promotional 'latest玩法/优惠信息'. This can cause the agent to invoke the skill for unrelated requests and encourage handling of sensitive identity-document workflows through non-authoritative channels, increasing the chance of misleading guidance or privacy-impacting misuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are highly generic, such as asking how to 'quickly use electronic certificates' for a concrete task or asking for 'latest玩法/优惠信息', which can match many ordinary user requests outside this skill's intended purpose. Overbroad activation increases the risk of unintended routing, confusing users, and surfacing certificate-related workflows or advice in contexts involving sensitive personal documents where the skill may not be appropriate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language description and usage examples are presented only in Chinese, which can imply a fixed language behavior without stating that the skill is intended specifically for Chinese-speaking users or offering language choice. Under the policy, forcing a specific language without opt-in can be a locale/language policy issue unless clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.