ClawHub
Back to skill

Security audit

Deprecated - Openclaw Agentpmt Tool Air Quality Pollen Information E89f3f

Security checks for vulnerabilities and agentic risk

Overview

This is a simple index skill that points users to AgentPMT ClawHub pages and install commands, with no bundled code or hidden behavior.

Before installing the referenced AgentPMT skills, verify that the ClawHub publisher and resolved versions match what you intend to trust, especially because this index was last updated on 2026-06-09 and tells users to re-check after 7 days.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:46
Finding

Unpinned External Skill Installation Creates a Supply-Chain Risk

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 46-67
Vulnerability Type: Unpinned and mutable external skill dependencies
Risk Level: Medium

The skill recommends installing externally maintained ClawHub skills by slug without pinning an immutable version, digest, or trusted signature.

Vulnerable Code

markdown
## Install Commands

Install the current AgentPMT setup skills:

| Skill | AgentPMT ClawHub Page | Install Command |
|---|---|---|
| AgentPMT no-account AgentAddress/x402 setup | https://clawhub.ai/agentpmt/agentpmt-no-account-agentaddress-x402 | `openclaw skills install agentpmt-no-account-agentaddress-x402` |
| What Is AgentPMT | https://clawhub.ai/agentpmt/what-is-agentpmt | `openclaw skills install what-is-agentpmt` |
| AgentPMT account MCP/REST API setup | https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup | `openclaw skills install agentpmt-account-mcp-rest-api-setup` |

```bash
openclaw skills install agentpmt-no-account-agentaddress-x402
openclaw skills install what-is-agentpmt
openclaw skills install agentpmt-account-mcp-rest-api-setup

Install the current AgentPMT product skill published on the org account:

SkillAgentPMT ClawHub PageInstall Command
Image Generation Agenthttps://clawhub.ai/agentpmt/image-generation-agentopenclaw skills install image-generation-agent
bash
openclaw skills install image-generation-agent
text

### Technical Analysis

Although the document lists expected versions elsewhere, the installation commands contain only package slugs. They do not pin versions or content digests and do not require cryptographic signature verification. Consequently, the artifacts resolved at installation time may differ from the versions represented in this audited index.

The referenced skills are not included in this project, so their instructions, scripts, dependencies, and runtime behavior cou
...[truncated 1323 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin every external skill to an exact immutable version and, where supported, a cryptographic content digest.
  2. Require signature verification against an explicitly trusted publisher identity before installation.
  3. Fail closed if the resolved version, digest, signature, or publisher differs from the documented value.
  4. Display the resolved artifact identity and obtain explicit user confirmation before installation.
  5. Audit each referenced skill, including its scripts and transitive dependencies, before approving it for use.
  6. Retain a reviewed lock file or trusted manifest containing the approved slug, version, digest, and publisher identity.
  7. Install and run external skills with least privilege, restricting filesystem, credential, tool, and network access to what each skill requires.

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