ClawHub
Back to skill

Security audit

apocdata

Security checks across malware telemetry and agentic risk

Overview

This is mostly a public stock-data skill, but its bundled install path uses remote shell/archive fetching that can persistently change local agent skills without integrity checks.

Install only from a release you trust, avoid the curl-to-bash path, and prefer downloading the archive or script first, inspecting it, and verifying integrity before placing files in your agent skills directory. The data API behavior itself appears read-only and no-auth, but the installer can persistently alter local agent behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares no permissions, yet its instructions include shell execution, local file reads, and local file writes via installation commands that create directories and extract a remote tarball into ~/.claude/skills. This mismatch is dangerous because it obscures the real capability footprint from users and reviewers, increasing the chance that an agent executes filesystem-changing commands without informed consent.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The stated purpose is a read-only A-share data skill, but the content also instructs downloading and extracting code from GitHub into the local skills directory and references update behavior that modifies README metadata. That description-behavior mismatch is dangerous because users may authorize a seemingly harmless market-data skill while it performs persistent local changes and remote content installation, which materially expands supply-chain and persistence risk.

External Script Fetching

Low
Category
Supply Chain
Content
#!/usr/bin/env bash
# ApocData Skill — one-line installer
# Usage: curl -sL https://raw.githubusercontent.com/ApocData/ApocData-skill/v2.0.0/scripts/install.sh | bash
set -euo pipefail

VERSION="${APOCDATA_VERSION:-v2.0.0}"
Confidence
89% confidence
Finding
curl -sL https://raw.githubusercontent.com/ApocData/ApocData-skill/v2.0.0/scripts/install.sh | bash

Chaining Abuse

High
Category
Tool Misuse
Content
#!/usr/bin/env bash
# ApocData Skill — one-line installer
# Usage: curl -sL https://raw.githubusercontent.com/ApocData/ApocData-skill/v2.0.0/scripts/install.sh | bash
set -euo pipefail

VERSION="${APOCDATA_VERSION:-v2.0.0}"
Confidence
95% confidence
Finding
| bash

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.