Back to skill

Security audit

凯米心跳插件

Security checks for vulnerabilities and agentic risk

Overview

The skill itself is a simple UI heartbeat indicator, but its install instructions rely on unpinned external package execution that is not fully represented by the reviewed files.

Review the install command before running it. Prefer a pinned and trusted `clawhub` CLI/plugin version, install in a low-privilege or isolated environment, and expect a Chinese-language UI indicator that mainly adds visual styling rather than verified real-time agent status.

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:94
Finding

Unpinned Third-Party Package Execution via npx

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 94
Vulnerability Type: Unpinned and externally resolved installation dependency
Risk Level: Medium

Vulnerable Code

markdown
## Installation

1. Place this plugin folder in OpenClaw's `skills/` directory.
2. Run `npx clawhub install kemi-heartbeat-plugin`.
3. Refresh the Web UI to display the heartbeat indicator.

Technical Analysis

The installation instructions invoke the clawhub command through npx without specifying an exact package version or integrity value. If the command is not already available locally, npx may retrieve and execute the current package published under that name. The command then installs another mutable, name-resolved component, kemi-heartbeat-plugin.

Consequently, the code executed during installation is not fully represented by the audited project files and may change after this review. Compromise of the relevant registry account, dependency infrastructure, package namespace, or a transitive dependency could cause users following the documented instructions to execute altered code.

The reviewed package itself contains only SKILL.md and _meta.json; no locally packaged executable implementation was available to verify the behavior of the external installer or installed component.

Attack Path

  1. An attacker compromises or gains control of the package resolved as clawhub, the named plugin, or one of their executable dependencies.
  2. The attacker publishes a malicious or modified version under the same mutable package name.
  3. A user follows the documented installation procedure and runs npx clawhub install kemi-heartbeat-plugin.
  4. npx resolves and executes the externally supplied CLI package, and the CLI resolves the named plugin.
  5. Malicious CLI code, installation hooks, lifecycle scripts, or plugin setup logic executes with the privileges of the user running the command.
  6. The payload may access resources available to that ...[truncated 828 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the clawhub CLI to a reviewed exact version rather than relying on the latest registry resolution:

    bash
    npx --yes clawhub@EXACT_REVIEWED_VERSION install kemi-heartbeat-plugin@EXACT_REVIEWED_VERSION
    
  2. Pin the plugin itself to an immutable version, commit, or content digest if the installer supports it.

  3. Publish and verify package integrity hashes or signed provenance before execution.

  4. Document the expected package registry and prevent fallback to untrusted or user-controlled registries.

  5. Prefer a locally installed, lockfile-controlled CLI over runtime package retrieval through npx.

  6. Disable dependency lifecycle scripts where compatible with the installation process.

  7. Review the complete CLI package, installed plugin payload, and transitive dependency graph before recommending execution.

  8. Run installation with a minimally privileged account in an isolated environment without production credentials or sensitive environment variables.

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown description presents the skill entirely in Chinese for user-facing messaging, including the status labels shown in the UI. The policy requires avoiding forced language or locale constraints unless the skill offers opt-in or clearly documents a justified region-specific limitation, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The injected indicator text and activation log are hard-coded Chinese user-facing strings, which means users receive a specific language experience regardless of preference. No alternative locale, configuration option, or documented justification is provided in the file.

Content

No source excerpt is available for this finding.

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.

Content

No source excerpt is available for this finding.