Back to skill

Security audit

AKM Fitness

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed fitness-planning skill made of Markdown prompts, with no malicious code found, though it asks for health-related details and uses an unpinned install command users should review.

Before installing, review the resolved repository contents and prefer a pinned commit or verified release instead of the mutable npx/GitHub command. When using the skill, avoid sharing unnecessary medical history and do not treat its output as diagnosis, rehabilitation care, or a substitute for a qualified clinician.

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:42
Finding

Unpinned npm CLI Executes Against a Mutable Third-Party Repository

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:42, with the same command duplicated in README.md:53, README.zh-CN.md:53, and clawhub-copy.md:14
Vulnerability Type: Supply-chain risk caused by unpinned executable tooling and a mutable remote source
Risk Level: Medium

Vulnerable Code

bash
npx skills add https://github.com/sirsws/akm --skill akm-fitness-planner --full-depth

Technical Analysis

The installation command does not pin the skills npm CLI to an exact reviewed version. Depending on the local environment and npm cache, npx may retrieve and execute the package version currently resolved by the npm registry.

The GitHub source is also specified as a mutable repository URL rather than an immutable commit SHA or verified release artifact. Therefore, the installed content can change after this project snapshot has been reviewed. The --full-depth option may also retrieve more repository content than the minimum Skill directory, increasing the amount of unaudited material entering the installation process.

No malicious package, payload, or executable script was found in the supplied project. This finding concerns the trust and integrity of the documented future installation path, not confirmed malicious behavior in the audited files.

Attack Path

  1. An attacker compromises the npm account or distribution channel associated with the unpinned skills CLI, or compromises the referenced GitHub account or repository.
  2. The attacker publishes modified CLI behavior or changes repository content after this snapshot was audited.
  3. A user follows the documented installation command.
  4. npx resolves and executes the then-current CLI package.
  5. The CLI retrieves content from the mutable repository reference, potentially including content that was not part of this audit.
  6. The altered installer or imported Skill content executes or influences the agent with the user's available pri ...[truncated 767 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the npm CLI to an exact reviewed version:

    bash
    npx skills@<exact-reviewed-version> add ...
    
  2. Replace the mutable repository reference with an immutable, reviewed commit SHA or signed release tag supported by the installer.

  3. Publish a checksum or cryptographic signature for the expected Skill artifact and verify it before installation.

  4. Remove --full-depth unless full repository traversal is strictly required. Retrieve only the specific Skill directory and necessary files.

  5. Document the exact npm package version, repository commit, and expected artifact digest used during security review.

  6. Apply the corrected command consistently in SKILL.md, README.md, README.zh-CN.md, and clawhub-copy.md.

  7. Consider installing the CLI as a reviewed dependency under a lockfile rather than allowing npx to resolve tooling dynamically.

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 (36)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · ELICITATION_PROMPT.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · ELICITATION_PROMPT.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · EXECUTION_PROMPT.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · EXECUTION_PROMPT.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · INPUT_TEMPLATE.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · INPUT_TEMPLATE.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · PUBLISHING_CHECKLIST.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · PUBLISHING_CHECKLIST.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · README.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · RECORD_TEMPLATE.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · RECORD_TEMPLATE.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SAMPLE_RECORD.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SAMPLE_RECORD.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · agent-store-copy.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · clawhub-copy.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · clawhub-copy.zh-CN.md (reported line 1)May include surrounding context.

md
<!--
文件:clawhub-copy.zh-CN.md
核心功能:作为 Fitness skill 的中文长版发布页文案,供 ClawHub / OpenClaw 或同类技能市场直接复用。
输入:Fitness 分支的 AKM 定位、方法结构与使用边界。

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The prompt explicitly asks for health-related details such as pain, injuries, joint/spine limits, medical prohibitions, and recovery issues, which are sensitive personal data. There is no accompanying notice about why this information is needed, how it will be used, whether it will be stored, or whether the user can avoid answering, creating a real privacy and consent risk in a fitness context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language comment states this file serves as the English execution prompt for the Fitness branch. Under the policy, forcing a specific language without user opt-in or a clearly justified locale constraint is a language-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file metadata and content describe this as a Chinese execution prompt (zh-CN / 中文执行提示词), but there is no natural-language indication that the user may choose another language or opt in to this locale. Under the policy for natural-language violations, forcing a specific language without user choice can be a locale policy issue.

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.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The README instructs users to install and execute a remote skill directly from GitHub via npx skills add without any version pinning, commit pinning, or integrity verification. That creates a supply-chain risk: the referenced repository or package resolution can change over time, causing users to fetch different code than was originally reviewed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The header states this is a Chinese sample for Chinese-facing pages and reviewers, and the entire document is provided only in Chinese. Under the policy, forcing a specific language without user opt-in or a clearly justified locale constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.