Back to skill

Security audit

Ai Intel Radar Repo

Security checks for vulnerabilities and agentic risk

Overview

This is a small, disclosed AI-news briefing skill that guides source selection and output format without adding code execution, persistence, credential use, or privileged actions.

Install this if you want a Chinese-first AI intelligence briefing workflow. Expect it to browse public AI news and research sources when used; ask explicitly for another language or format if needed.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction 'Produce concise, decision-ready AI intelligence in Chinese by default' imposes a language preference on users without indicating that they can choose another language. This is a natural-language policy concern because the skill sets a locale/language behavior by default rather than offering opt-in or selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file introduces Chinese-language source channels and later requires uncertain information to be flagged with the Chinese phrase "待验证". This imposes a specific language in the workflow without stating that users can choose their preferred language or locale.

Content

No source excerpt is available for this finding.