ClawHub
Back to skill

Security audit

Daily News

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple daily-news helper that runs a local script to fetch public news from one disclosed API, with no evidence of hidden access, persistence, or credential handling.

Install this if you want a lightweight news briefing helper that contacts the 60s API. Be aware it uses a shell script with curl and sends the requested date/format to that external service, so review or constrain shell/network permissions if your environment requires strict least privilege.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill invokes a shell script (`./scripts/news.sh`) but does not declare any tool scope or allowed-tools constraints in the skill metadata. This weakens least-privilege boundaries and can let an agent execute shell-capable behavior without an explicit permission declaration, increasing the risk of unexpected command execution if the skill or surrounding orchestration is modified or abused.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The metadata says the skill is for world news in Chinese, which can override user preference and lead to unwanted language-constrained output. While not a direct code-execution issue, it is a policy and safety concern because it may cause the agent to disregard user intent or accessibility needs, especially when users expect responses in another language.

Static analysis

No suspicious patterns detected.