ClawHub
Back to skill

Security audit

Ai News Collectors 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language AI news aggregation skill that uses web search and source fetching as expected, with no executable code, persistence, credential access, or hidden high-impact behavior found.

Install this if you want Chinese AI-news digests and are comfortable with the agent performing multiple web searches and fetching public news sources before answering. Users who prefer another language may need to explicitly request it.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger description is broad and matches very common AI-news style requests without clear scoping or exclusion rules, which can cause the skill to activate when a more general assistant response would be safer or more appropriate. Over-broad invocation can lead to unexpected tool use, unnecessary external fetching, and user-intent hijacking, especially because the workflow mandates extensive searching before answering.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Forcing Chinese output regardless of the user's language preference can override user intent and degrade reliability, particularly if the skill is triggered for multilingual or English requests. While not a direct code-execution issue, it is a policy and usability weakness that can cause unauthorized transformation of outputs and make the agent behave unexpectedly.

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 presents all headings, descriptions, and search guidance exclusively in Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue unless the regional constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.