ClawHub
Back to skill

Security audit

新闻订阅

Security checks for vulnerabilities and agentic risk

Overview

This news RSS skill is not clearly malicious, but it asks for shell execution and generic API-key setup that are not well justified for public headline fetching.

Review this skill before installing. Use it only if you are comfortable granting command execution, avoid setting a generic API_KEY unless the publisher documents exactly what service needs it, and prefer running it in a constrained environment if using custom RSS URLs or export paths.

SkillSpector

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

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill declares `exec` capability even though its stated purpose is only to fetch and summarize RSS headlines. Unnecessary shell execution expands the attack surface substantially: if any downstream implementation interpolates user-controlled fields such as custom RSS URLs, export paths, or filters into commands, it can enable command execution or arbitrary local actions.

Context-Inappropriate Capability

Medium
Confidence
79% confidence
Finding
The documentation introduces API key handling and environment-variable setup even though the described functionality is public RSS retrieval, which normally does not require secrets. This mismatch can mislead operators into injecting sensitive credentials into the skill environment, increasing the risk of accidental disclosure through logs, prompts, shell commands, or unrelated tool usage.

Static analysis

No suspicious patterns detected.