ClawHub
Back to skill

Security audit

Threads Profile Search

Security checks across malware telemetry and agentic risk

Overview

The skill searches Threads profiles and enriches profile metadata in a way that is mostly disclosed and aligned with its stated purpose.

Before installing, understand that the skill can navigate Threads and call a Threads profile API from your active browser session, so any existing Threads login state may be used for those requests. Treat the output as profile data collection and avoid using it for sensitive, non-consensual, or policy-restricted scraping workflows.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill performs browser-driven navigation and API-backed profile enrichment, which are network-capable actions, yet no permissions are explicitly declared. This creates a transparency and governance gap: operators may authorize or invoke the skill without realizing it can make outbound requests and fetch additional data beyond simple page reading.

Description-Behavior Mismatch

Low
Confidence
91% confidence
Finding
The stated scope emphasizes profile search and a limited field set, but the enrichment flow also collects following_count and external_url. That scope drift increases data collection beyond what a user may reasonably expect, which can lead to overcollection and misuse of extra profile metadata.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The skill claims it only reads data already displayed to the user on the page, but it also invokes profile API fetches to obtain additional data. This is a misleading boundary statement that can cause reviewers or users to underestimate the skill’s reach and the privacy/compliance implications of hidden network retrieval.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill persists operational notes to a local memory file without upfront disclosure in the main description. Even though it says not to store keywords or result counts, any persistent write capability can still retain unexpected execution details that may reveal sensitive context or create audit/privacy concerns.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.