ClawHub
Back to skill

Security audit

Yyh211 Daily Ai News

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AI-news briefing helper that uses web search and article fetching, with no evidence of hidden code, credential access, persistence, or destructive behavior.

Install this if you want an agent to fetch and summarize current AI news from public websites. Be aware it may run web searches for broad requests like AI updates, so users who want tighter control should invoke it only for explicit daily news briefings.

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
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation criteria include broad, everyday phrasing such as wanting to know what's happening in AI, which can cause the skill to trigger when the user did not explicitly request a news-aggregation workflow. Unintended activation can lead to unnecessary web access, irrelevant responses, and accidental invocation in contexts where the user wanted general discussion rather than external retrieval.

Vague Triggers

Low
Confidence
83% confidence
Finding
The README says the skill activates when a user asks for phrases like 'AI updates' or 'latest AI developments', which are broad natural-language requests rather than tightly scoped invocation triggers. The description also does not provide exclusion conditions or negative examples, so it is unclear when these phrases should invoke the skill versus normal conversation.

Static analysis

No suspicious patterns detected.