ClawHub
Back to skill

Security audit

top-rss-list

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown-only RSS recommendation skill with minor routing and language-preference issues but no evidence of harmful behavior.

Before installing, be aware that generic words like top or common topic names may route requests to this skill unexpectedly, and it may answer bilingually even when you prefer one language. It appears low risk because it only provides RSS recommendations and OPML text, with no local execution or credential access.

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
96% confidence
Finding
The trigger phrases are broad enough to match common conversational words like “top”, “热门”, or category names, which can cause the skill to activate when the user did not explicitly intend to use it. This creates prompt-routing ambiguity and may override the user’s real request, especially in multi-skill environments where accidental invocation can degrade reliability or expose unrelated context to the skill.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
Forcing bilingual Chinese/English output regardless of user preference is not a direct security flaw, but it is a genuine policy/control weakness because it removes user choice and can cause unintended disclosure, formatting bloat, or prompt-routing side effects in constrained contexts. In practice, this is mainly a usability and compliance issue rather than a severe exploit path, and the RSS recommendation context makes it less dangerous than in skills handling sensitive or regulated data.

Static analysis

No suspicious patterns detected.