ClawHub
Back to skill

Security audit

TokenLab Model Picker

Security checks for vulnerabilities and agentic risk

Overview

This is a small model-selection guidance skill that uses TokenLab's public catalog and does not include executable code, persistence, credential access, or hidden behavior.

Before installing, consider pinning or verifying the skills CLI and repository source instead of using the unpinned non-interactive command. When using the skill, expect it to contact TokenLab's public API to look up model and pricing data, and avoid putting sensitive private prompts into catalog query parameters.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The README recommends running npx skills add ... -y without pinning the package or tool version, which can cause users to execute whatever version is currently resolved from the registry at install time. This creates a supply-chain risk: a compromised upstream package, typo-squatted dependency, or breaking change could lead to unintended code execution during installation or skill retrieval.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
1. Identify the workload: chat, coding, agent loop, image, video, audio, embedding, rerank, translation, decisions, or multimodal.
2. Use the public model catalog before recommending hardcoded IDs:
   - General catalog: `GET https://api.tokenlab.sh/v1/models`
   - Task shortlist: `GET https://api.tokenlab.sh/v1/models?recommended_for=<scene>`
   - Model contract: `GET https://api.tokenlab.sh/v1/models/:model`
   - Pricing detail: `GET https://api.tokenlab.sh/v1/models/:model/pricing`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
1. Identify the workload: chat, coding, agent loop, image, video, audio, embedding, rerank, translation, decisions, or multimodal.
2. Use the public model catalog before recommending hardcoded IDs:
   - General catalog: `GET https://api.tokenlab.sh/v1/models`
   - Task shortlist: `GET https://api.tokenlab.sh/v1/models?recommended_for=<scene>`
   - Model contract: `GET https://api.tokenlab.sh/v1/models/:model`
   - Pricing detail: `GET https://api.tokenlab.sh/v1/models/:model/pricing`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
1. Identify the workload: chat, coding, agent loop, image, video, audio, embedding, rerank, translation, decisions, or multimodal.
2. Use the public model catalog before recommending hardcoded IDs:
   - General catalog: `GET https://api.tokenlab.sh/v1/models`
   - Task shortlist: `GET https://api.tokenlab.sh/v1/models?recommended_for=<scene>`
   - Model contract: `GET https://api.tokenlab.sh/v1/models/:model`
   - Pricing detail: `GET https://api.tokenlab.sh/v1/models/:model/pricing`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
1. Identify the workload: chat, coding, agent loop, image, video, audio, embedding, rerank, translation, decisions, or multimodal.
2. Use the public model catalog before recommending hardcoded IDs:
   - General catalog: `GET https://api.tokenlab.sh/v1/models`
   - Task shortlist: `GET https://api.tokenlab.sh/v1/models?recommended_for=<scene>`
   - Model contract: `GET https://api.tokenlab.sh/v1/models/:model`
   - Pricing detail: `GET https://api.tokenlab.sh/v1/models/:model/pricing`

Static analysis

No suspicious patterns detected.