ClawHub
Back to skill

Security audit

ORF news

Security checks for vulnerabilities and agentic risk

Overview

This is a single-file ORF RSS news-formatting skill that fetches public feeds and does not request sensitive access or persistence.

Installers should expect the skill to fetch public ORF RSS feeds when ORF headlines are requested. If they use broad Austria-news prompts, the agent may prefer ORF even when another source was intended, so users should name the desired source explicitly.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill's 'When to use' examples are broad enough to match common, generic news queries such as 'ORF News' or 'was läuft bei ORF', which can cause the agent to invoke this skill opportunistically in situations where the user may have intended a broader or different news source. This is not code execution or data exfiltration, but it can create over-selection risk, reducing routing precision and causing misleading responses if the skill is chosen too aggressively.

Static analysis

No suspicious patterns detected.