ClawHub
Back to skill

Security audit

AI Intel Radar

Security checks for vulnerabilities and agentic risk

Overview

This is a benign AI news briefing skill with mild usability caveats around broad activation wording and Chinese-by-default output.

Install this if you want structured AI news briefs, especially in Chinese. Be aware it may activate on broad requests for latest AI news or market updates, and you should specify language, timeframe, and source preferences when needed.

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
Confidence
92% confidence
Finding
The skill description uses very broad trigger phrases like latest AI news, trend monitoring, market updates, and scouting reports, which can match many ordinary user requests and cause over-invocation. This increases the chance the agent routes users into this skill when they did not explicitly ask for it, leading to unwanted web-driven behavior, scope creep, and reduced reliability of responses.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
Forcing Chinese output by default without user opt-in can override user expectations and system language preferences, creating misleading or unusable output for users who did not request Chinese. In a broadly activated skill, this becomes more dangerous because accidental invocation can unexpectedly transform response language and reduce transparency or comprehension.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
Line L37 instructs the skill to flag uncertain information with the Chinese phrase "待验证". This imposes a specific language choice in the skill content without stating that the user can choose the locale or that the skill is intended only for Chinese-language workflows.

Static analysis

No suspicious patterns detected.