ClawHub
Back to skill

Security audit

研究任务与场景界定

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language research scoping helper that reads bundled reference markdown and produces task-scope outputs, with no executable code, persistence, credential access, or hidden network behavior found.

Install this if you want Chinese-language Wiki research task scoping. Review the generated scope files before using them downstream, especially for public claims, rankings, endorsements, or government-facing work, because the skill frames those as higher-evidence scenarios but does not perform the evidence collection itself.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises activation on a very broad set of common intents, including generic research, policy, feasibility, market entry, ranking, and consulting scenarios, without clear exclusion criteria or tight routing boundaries. This can cause over-triggering, misrouting sensitive requests into this skill, and unintended handling of external-claims or ranking/backing use cases that require stricter controls.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains natural-language instructions that implicitly require Chinese proficiency, but it does not provide user opt-in, alternatives, or a justification for restricting the skill to a specific language or locale. Under the policy rule for natural-language violations, forcing a specific language without user choice is reportable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file instructs that all customer-visible text must use Chinese, which is a natural-language locale restriction. Because it does not provide an opt-in, user choice, or a clear region-specific justification, it violates the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest's natural-language description is entirely in Chinese and specifies the skill's behavior in a way that implies a fixed language/locale context, but it does not state that users can choose another language or that the restriction is intentional and justified. This can violate language/locale policy when skills are expected to support user preference unless explicitly limited.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
61% confidence
Finding

The instruction says the L1-L5 rules must remain internal and should not be explained in customer-visible text. While not a direct locale restriction, it is a natural-language communication constraint affecting what can be disclosed to users, and it is not presented as user choice or justified policy text.

Content

No source excerpt is available for this finding.