ClawHub
Back to skill

Security audit

x-algorithm-optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local writing-assistant skill for X posts, with dual-use ranking and moderation detail that should only be used for legitimate, policy-compliant content.

Before installing, be comfortable with a skill that gives detailed advice about X ranking and suppression mechanics. Use it for genuine posts and policy compliance, not spam, harassment, synthetic engagement, or trying to sneak violating content past safety systems.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (4)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

Despite the disclaimer, this file provides a detailed map of platform suppression triggers, labels, and operational thresholds specifically so creators can avoid classifier-triggered enforcement. That is effectively actionable evasion guidance: it tells users how to modify content, links, media, and account behavior to preserve distribution while skirting safety systems, which can be exploited by spammers, harassers, and other abusive actors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The 'Creator takeaways' and final checklist convert internal moderation and ranking mechanics into step-by-step instructions for minimizing detection and suppression. In the context of a skill whose purpose is optimizing reach on X, this becomes more dangerous because the advice is directly usable to tune borderline, spammy, or abusive content for maximum distribution without triggering platform defenses.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 48)May include surrounding context.

md
## 🧠 What it does

Point your agent at this skill and ask it to write or review a post. It reads
X's published ranking code and drafts or critiques your post against the real
scoring weights, retrieval paths, and suppression rules, runs a negative-signal
audit, and explains the exact mechanism behind every suggestion. The result is

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document explicitly describes use of sensitive and inferred user attributes such as exact age, gender, geolocation, country, installed apps, and inferred interests for ranking, but provides no privacy warning, consent boundary, or handling constraints. In the context of a skill that operationalizes growth tactics from ranking internals, this normalizes privacy-invasive profiling and could encourage downstream use or replication of sensitive-targeting practices without adequate disclosure or compliance review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.