Claude Code API Optimizer Skill

• Outcome: Review
• Latest audit: Sep 16, 2026 · 4:17 AM UTC
• Version: 1.0.0

Overview

The skill is a cost-saving guide, but it asks agents to persist user and project memories and use secondary models without enough consent, privacy, or source-trust controls.

Install only if you are comfortable with persistent memory files. Require review and approval of proposed memories, block secrets and sensitive personal data, restrict writes to a dedicated memory directory, choose any secondary model/provider explicitly, and treat stored memories as user-editable notes rather than trusted instructions.

A.I.G

Vulnerability Patterns

• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (1)

T02 · Agent Memory Poisoning

Warning

• Location: SKILL.md:66

Finding

Untrusted Conversation Content Can Be Persisted as Long-Term Agent Memory

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 183)May include surrounding context.

md

1. **Copy this skill** into your agent's skill directory (or paste `SKILL.md` into your system prompt).

External Model or Provider Selection

Medium

• Category: Excessive Agency
• Confidence: 90% confidence

Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 7)May include surrounding context.

md

version: 1.0.0
author: OpenClaw Community
tags: [optimization, tokens, cost-reduction, context-management, memory]
model: any
---

# Token Optimizer

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill explicitly instructs agents to extract and persist user-related information such as preferences, expertise, and project context into memory files, but it provides no privacy guardrails, consent requirements, retention limits, or restrictions on sensitive data. In practice this can lead to unnecessary storage of personal or behavioral data across sessions, increasing privacy, compliance, and data leakage risk if memory files are exposed or reused inappropriately.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.