ClawHub
Back to skill

Security audit

Social Scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a passive reference helper that prints documentation and does not access credentials, network resources, files, or persistent system settings.

This appears safe to install as a documentation reference skill. Be aware that its short command names may overlap with other skills or normal requests, so invoke it explicitly when possible.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/script.sh (reported line 64)May include surrounding context.

sh
## Prerequisites
- Basic understanding of data concepts
- Required tools and access credentials
- System meeting minimum requirements

## Installation

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The command triggers are single common words like 'intro', 'security', and 'patterns', which are highly likely to collide with ordinary user language or other skills' commands. In an agent environment, this can cause accidental invocation of this skill when the user intended something else, leading to prompt-routing confusion and unintended tool behavior even though the skill itself is otherwise passive reference content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.