ClawHub
Back to skill

Security audit

social-media-research

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does public social-media research as advertised, but its helper script can call arbitrary Crawlora API paths and methods beyond the documented social-media scope.

Review this before installing if you expect a tightly scoped social-media-only helper. Use it only with non-sensitive public research targets, understand that queries go to Crawlora under your API key, and avoid relying on the included script as a constrained wrapper unless you add endpoint and method allowlisting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
79% confidence
Finding
A skill advertised as narrowly scoped to social-media research becomes materially riskier if its wrapper actually allows arbitrary Crawlora endpoints and caller-controlled POST bodies. That creates a confused-deputy problem: users and reviewers may trust the skill with broader network/API authority than disclosed, enabling access to unrelated data sources, unexpected actions, or policy bypass through the generic proxy behavior.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The file instructs callers to send user-supplied identifiers and queries to a third-party API using an API key, but it provides no user-facing warning about external data transmission. In a research skill, users may input sensitive names, handles, or investigation targets; silently forwarding those to Crawlora creates privacy, compliance, and data-handling risk.

External Transmission

Medium
Category
Data Exfiltration
Content
Endpoints this skill uses, grouped by platform. Call them via `scripts/crawlora.sh` (see SKILL.md).

All paths are relative to the API base `https://api.crawlora.net/api/v1` and require the header `x-api-key: $CRAWLORA_API_KEY`. Path params like `{id}` are substituted into the URL; `GET` params go in the query string; `POST` params go in a JSON body.

**67 endpoints across 9 platform group(s).**
Confidence
82% confidence
Finding
https://api.crawlora.net/

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:23