ClawHub
Back to skill

Security audit

gate-news-briefing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only crypto news briefing workflow with clear tool boundaries; its main caveat is that one general news query defaults to English, which may limit coverage.

Install only if you are comfortable using the Gate-News MCP server for read-only crypto news, events, and sentiment lookups. For non-English or region-specific news, be aware that the general briefing path may favor English sources unless the skill is adjusted.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
## General Rules

⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding.
Do NOT select or call any tool until all rules are read. These rules have the highest priority.
→ Read `./references/gate-runtime-rules.md`
→ Also read `./references/info-news-runtime-rules.md` for gate-info / gate-news shared rules (tool degradation, report standards, security, and output standards).
- **Only call MCP tools explicitly listed in this skill.** Tools not documented here must NOT be called, even if they
Confidence
80% confidence
Finding
Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill hard-codes `lang="en"` for news search results, which can silently exclude relevant non-English reporting and override the user's language preferences. In a news skill, this creates a content-selection bias and can reduce completeness or accuracy of the briefing, especially for region-specific events first reported in local-language sources.

Static analysis

No suspicious patterns detected.