ClawHub
Back to skill

Security audit

Save Image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward helper for downloading web images and media, with expected network access and local file writes but no hidden persistence or unrelated authority.

Install only if you want the agent to help download media from web URLs. Review URLs before fetching, avoid login-gated or private content unless you explicitly intend to use it, and choose output paths carefully because downloads can create or overwrite local files.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description is excessively broad, matching common phrases like "download image", "save image", and "get this image," which can cause the skill to activate in many ordinary contexts beyond its intended scope. Overbroad auto-invocation increases the chance the agent will perform network-fetching behavior unexpectedly, including scraping pages and spoofing browser headers/referers, which expands the attack surface and may bypass safer default handling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This section shows yt-dlp commands that save videos, audio, and thumbnails into the user's Downloads directory, which is a user-data-affecting file write. The surrounding markdown provides usage examples but does not include any warning or disclosure about local file creation, overwriting considerations, or verifying the source URL before download.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The curl examples download remote images and save them via '-o ', which affects the local filesystem and pulls untrusted remote content. The documentation explains how to do this but does not warn that the commands will create or overwrite local files or that the retrieved content should be treated as untrusted.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.