Security audit

xclaw

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it extracts X posts and saves a local report with media, with privacy and storage considerations users should understand.

Before installing, understand that this skill may use your logged-in X session to read your home timeline and will save post text, metrics, URLs, and downloaded media locally under ../../intel/x. Use it only for content you are allowed to collect and archive.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill is designed to scrape the user's X home timeline or profiles and store the resulting content locally, but it provides no privacy warning or consent checkpoint despite potentially handling personal, sensitive, or account-specific data. In context, scraping a home timeline is more dangerous than scraping a public page because it may include personalized content, recommendations, and account-linked information the user did not intend to archive.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly instructs downloading remote media files and writing them into local directories without requiring a user confirmation or warning about filesystem side effects. This is risky because it causes persistent local changes and pulls untrusted remote content to disk, which can surprise users and create privacy, storage, or compliance issues.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The required output format hard-codes the timestamp as Asia/Shanghai, which imposes a specific locale/timezone choice. There is no indication that the user can opt into this locale or that the constraint is required for a region-specific purpose.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.