Security audit

Quantum Distribution Generator

Security checks for vulnerabilities and agentic risk

Overview

The statistical tool itself is coherent, but it should be reviewed because it tells agents to trust mutable remote instructions and includes unpinned installer commands.

Review this skill before installing. Use the ClawHub/OpenClaw install route where possible, avoid unpinned npx setup commands unless you trust the source at execution time, and do not let remote get_instructions responses override your normal safety, credential, or tool-use policies.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:95
Finding: Mutable Remote Instructions Can Override the Audited Skill
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:164
Finding: Unpinned Package and Skill Installation Creates a Supply-Chain Execution Risk
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (10)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation keywords include generic terms like beta, source, and count, which are common in unrelated contexts. That can cause accidental skill invocation and unintended external tool usage, especially in agent frameworks that auto-select skills based on keyword matching.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: The skill recommends installing supporting skills via npx skills without pinning an exact package version or commit. That creates a supply-chain risk: a future compromised or breaking release could be fetched and executed at install time, especially because npx may download and run remote code automatically.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: This line contains an unpinned npx skills install command, which can cause users or agents to fetch and execute whatever version is current at runtime. In a skill ecosystem, that exposes consumers to package compromise, typosquatting, or unexpected behavior changes outside the reviewed skill content.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: The install instruction uses npx skills without version pinning, so execution depends on the latest upstream package state rather than the reviewed version. That weakens reproducibility and opens a supply-chain avenue if the package or dependency tree is later compromised.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: Another unpinned npx skills invocation appears in the skill body, creating the same remote code execution exposure during installation. Because the skill is instructing users how to bootstrap related tooling, this broadens the trust boundary to external package infrastructure.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: This reference again directs installation through an unpinned npx skills command. Even though it is documentation, agents or users may copy it directly, leading to execution of unreviewed package versions and potential compromise of the local environment.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 90% confidence
Finding: The same supply-chain weakness is present here: unpinned remote package execution via npx. Repetition across the document increases the likelihood that an agent or operator will use the unsafe path, making exploitation more plausible over time.
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 230)May include surrounding context.
md
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`) - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/quantum-distribution-generator - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase

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 231)May include surrounding context.
md
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`) - AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`) - Marketplace product: https://www.agentpmt.com/marketplace/quantum-distribution-generator - AgentPMT main MCP server: https://api.agentpmt.com/mcp/ - AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest description focuses on sampling named probability distributions and Monte Carlo use cases such as risk analysis, queuing theory, and A/B testing. The randomwalk action adds a distinct stochastic-process simulation capability that is not mentioned in the manifest's enumerated distributions or action summary, making the implemented skill broader than described.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.