ClawHub

X Apify

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it fetches public X/Twitter data through Apify, with normal privacy and cost considerations for a third-party API tool.

Install only if you are comfortable sending X/Twitter searches, usernames, and tweet URLs to Apify and the selected actor. Use a dedicated Apify token if possible, monitor credit usage, verify or override APIFY_ACTOR_ID because the docs and code disagree on the default actor, and use --no-cache or --clear-cache for sensitive lookups.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly requires access to environment variables, local file reads/writes for caching, and network access to Apify, but it does not explicitly declare permissions. This creates a transparency and consent problem: users may invoke the skill without realizing it can transmit data to a third party and persist data locally.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The description explains functionality and caching benefits but does not prominently warn that search queries, usernames, and tweet URLs are transmitted to Apify and may be retained in a local cache. This is a privacy risk because user-supplied inputs may contain sensitive investigation targets, internal research topics, or personal identifiers.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases are generic enough to match many ordinary user intents around Twitter/X search and retrieval, which can cause this skill to be selected unexpectedly. In a skill ecosystem, overbroad routing increases the chance that a skill handling external network access and paid API usage is invoked when a narrower or safer tool was intended, potentially causing unintended data access, scraping, or cost-incurring actions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal