ClawHub
Back to skill

Security audit

BBC Vietnamese Trendy News

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed BBC Vietnamese RSS headline fetcher with ordinary dependency and scope cautions, not evidence of malicious behavior.

Install only if you want BBC Vietnamese headlines and are comfortable with the agent running the disclosed local Python script to fetch live RSS content. For better assurance, pin dependency versions, remove unused packages, and treat results as sourced BBC RSS headlines rather than comprehensive global trending news.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (11)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill performs network-capable behavior to fetch external news content, but the manifest does not clearly declare or constrain that capability. Undeclared network access reduces transparency and reviewability, making it easier for a seemingly simple skill to reach external sources without explicit user or platform awareness.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding
The skill claims to provide latest trending global news, but the documented behavior is hardcoded to a specific BBC Vietnamese source and lacks logic for determining global relevance, trending status, or breaking significance. This mismatch can mislead users and reviewers about what data is collected and presented, undermining trust and creating room for deceptive or overbroad invocation.

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The manifest presents a narrow news-fetching function, but the documentation directs the agent to use a generic command-execution tool with shell command construction. Allowing raw shell execution for a simple content-fetching task expands the attack surface substantially, because the agent is being taught to invoke a general-purpose execution path rather than a tightly scoped news retrieval interface.

Context-Inappropriate Capability

High
Confidence
95% confidence
Finding
Using raw command execution is excessive for the stated purpose and creates a direct path to unintended shell behavior if any part of the command becomes influenceable. In this context, the unnecessary power of the execution mechanism makes the skill more dangerous than a normal news skill because compromise or prompt-induced misuse can turn a benign fetch operation into arbitrary command execution.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The instructions tell the agent to execute external commands and scripts without clearly disclosing that behavior to the user. Lack of transparency about subprocess execution prevents informed consent and makes risky operations appear like ordinary information retrieval, which is especially problematic given the skill's use of raw execution tooling.

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
bs4
requests
feedparser
Confidence
93% confidence
Finding
beautifulsoup4

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
bs4
requests
feedparser
Confidence
91% confidence
Finding
bs4

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
bs4
requests
feedparser
Confidence
98% confidence
Finding
requests

Unpinned Dependencies

Low
Category
Supply Chain
Content
beautifulsoup4
bs4
requests
feedparser
Confidence
97% confidence
Finding
feedparser

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
96% confidence
Finding
requests

Known Vulnerable Dependency: feedparser — 10 advisory(ies): CVE-2011-1157 (feedparser Cross-site Scripting vulnerability); CVE-2009-5065 (feedparser Cross-site Scripting vulnerability); CVE-2011-1158 (feedparser Cross-site Scripting vulnerability) +7 more

High
Category
Supply Chain
Confidence
95% confidence
Finding
feedparser

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.