ClawHub

Venetech News

Security checks across malware telemetry and agentic risk

Overview

This news-summarization skill is mostly coherent, but it includes scraping guidance that may bypass publisher access controls.

Install only if you are comfortable with a skill that fetches public news sources and may install Python parsing dependencies. Prefer RSS feeds and permitted public pages; avoid the rotating-proxy and undocumented internal-API guidance unless you have explicit authorization and the site's terms allow it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The guidance to use rotating proxies to access elpitazo.net despite frequent blocks encourages bypassing publisher access controls that are not necessary for a normal RSS/news summarization skill. Even if framed as reliability advice, it expands the skill from ordinary aggregation into evasion behavior, which could violate site terms, mask abusive traffic, and normalize stealthy collection practices.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
Suggesting use of an 'internal API' discoverable via DevTools goes beyond the declared editorial scraping scope and can lead operators to consume undocumented endpoints never intended for third-party automation. This increases the risk of unauthorized data access, brittle integrations, and circumvention of publisher controls or contractual boundaries.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation criteria are broad enough to trigger on generic requests for news, updates, summaries, or briefings, which can cause the skill to activate outside its intended niche. Over-broad auto-invocation is dangerous because it may route unrelated user requests into scraping workflows, increase unnecessary network access, and override more appropriate tools or user preferences.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill is written to operate in Spanish by default and strongly implies Spanish output, without checking the user's language preference. This is mainly a scope and UX safety issue rather than a direct security flaw, but forced language behavior can mis-handle requests, reduce transparency, and cause the agent to ignore explicit user preferences or surrounding system context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal