Back to skill

Security audit

Stone Acpx

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed guide for using the acpx CLI and does not show hidden, destructive, or unrelated behavior.

Before installing, prefer the pinned plugin-local acpx runtime for normal use. Only run npx acpx@latest in an isolated, intentional upgrade-check context, because it can execute whatever package version is current at that time.

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:19
Finding
Execution of a Mutable npm Package Version Through npx## Vulnerability Details **File Location**: `SKILL.md`, line 19 **Vulnerability Type**: `T08: Insecure Dependencies` **Risk Level**: Medium **Complete Code Snippet**: ```markdown - Use `npx acpx@latest` only for explicit manual experiments or upgrade checks, not as the default OpenClaw runtime backend. ``` ### Technical Analysis The skill permits `npx acpx@latest` for manual experiments and upgrade checks. The `latest` tag is mutable and does not identify a specific audited package artifact. When invoked, `npx` may retrieve and execute the package version currently associated with that tag, including its transitive dependencies and lifecycle behavior. Consequently, the effective executable payload can change after this skill has been reviewed. If the package publisher, npm account, registry distribution channel, release process, or dependency tree is compromised, following this instruction could execute unreviewed code locally. The instruction limits this command to explicit experiments or upgrade checks and separately recommends a pinned plugin-local runtime, reducing likelihood. However, it does not remove the supply-chain execution risk when the permitted exception is used. ### Attack Path 1. An operator requests a manual experiment or upgrade check. 2. The agent follows the permitted instruction and invokes `npx acpx@latest`. 3. `npx` resolves the mutable `latest` tag using the configured npm registry. 4. It downloads the current package release and any required dependencies if they are not already available locally. 5. A compromised or malicious release, dependency, or registry response executes under the invoking user's account. 6. The malicious code can act within that account's process, filesystem, network, and credential-access boundaries. ### Impact Assessment Successful exploitation could provide arbitrary code execution with the privileges of the user running `npx`. Depending on the local environment a ...[truncated 416 chars]
Remediation
## Remediation Suggestions - Remove the authorization to execute `npx acpx@latest`. - Use only the documented plugin-local binary backed by the managed, pinned dependency. - If a separate upgrade check is necessary, query package metadata without executing the package. - Test upgrades using an exact version in an isolated, least-privileged environment with no production credentials or sensitive repository access. - Verify package provenance and integrity before execution, including lockfile and integrity-hash validation. - Subject each proposed version and its transitive dependency changes to security review before updating the managed runtime. - Where supported, restrict package lifecycle scripts and outbound network access during validation.
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
Findings (3)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Skill Enumeration

Medium
Category
Agent Snooping
Content
For the full upstream reference, read:

- https://raw.githubusercontent.com/openclaw/acpx/main/skills/acpx/SKILL.md
- https://raw.githubusercontent.com/openclaw/acpx/main/docs/CLI.md
Confidence
80% confidence
Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Static analysis

No suspicious patterns detected.