Back to skill

Security audit

Zhang Yiming Perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only persona skill, but its README recommends an unpinned global npx install path that users should review carefully.

Install through the reviewed ClawHub path when possible, and avoid the unpinned global npx command unless you have separately reviewed the source and trust the current package/repository. Expect the skill to frame answers in a Zhang Yiming-style Chinese business/persona perspective, and invoke it explicitly when that framing is desired.

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
README.md:15
Finding

Unpinned Third-Party Installation with Global Scope

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 15-17
Vulnerability Type: Unpinned third-party package execution and global installation
Risk Level: Medium

Vulnerable Code

bash
npx skills add xie-jun/zhang-yiming-perspective -g

Technical Analysis

The documented installation procedure invokes the third-party skills package through npx without specifying an immutable package version. It also identifies the Skill repository through a mutable owner/name reference rather than a fixed commit hash and requests global installation through the -g option.

When executed, npx may retrieve and run the package version currently available from the configured npm registry. Consequently, the code executed at installation time can differ from the version reviewed during this audit. No lockfile, package integrity hash, repository commit, or signature is provided to authenticate the retrieved components.

There is no evidence in the audited project that the current package or repository is malicious. The vulnerability is the unsafe trust model of the documented installation process, which exposes users to package compromise, account takeover, malicious publication, or an upstream supply-chain incident.

Attack Path

  1. An attacker compromises the npm account or registry entry associated with the unpinned skills package, or compromises the mutable repository referenced by xie-jun/zhang-yiming-perspective.
  2. The attacker publishes a modified package version or replaces repository content with malicious installer logic.
  3. A user follows the README and executes:
    bash
    npx skills add xie-jun/zhang-yiming-perspective -g
    
  4. npx retrieves and executes the currently published package rather than a previously reviewed immutable version.
  5. The malicious installer runs with the permissions of the invoking user and performs a global installation.
  6. Attacker-controlled files, Skill instructions, or executable hooks ...[truncated 1007 chars]
Remediation
View remediation

Remediation Suggestions

  1. Prefer the platform-native installation command already documented by the project:

    bash
    clawhub install zhang-yiming-perspective
    
  2. If the npx installation method must remain, pin the CLI to a reviewed version:

    bash
    npx skills@<reviewed-version> add xie-jun/zhang-yiming-perspective@<immutable-commit>
    
  3. Replace mutable branch or repository references with an immutable commit hash or signed release tag.

  4. Publish and verify cryptographic integrity information, such as package integrity hashes, checksums, or signed release attestations.

  5. Remove -g unless global installation is strictly required. Prefer project-local or user-scoped installation to limit the affected scope.

  6. Document the expected package source, version, publisher identity, and verification procedure so users can detect registry substitution or account compromise.

  7. Add automated dependency and release provenance checks, including package signature verification and monitoring for unauthorized package-version changes.

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (11)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document presents all usage instructions, descriptions, and warnings exclusively in Chinese, which effectively imposes a specific language on users. Under the policy, language constraints should either offer user choice or be clearly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The README instructs users to run npx skills add xie-jun/zhang-yiming-perspective -g without pinning a specific version. This creates a supply-chain risk because the command will fetch whatever package/version is current at install time, so a compromised publisher account, typo-squatted dependency path, or malicious future release could execute unreviewed code on the user's system.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list contains broad, generic terms such as “算法思维” and “延迟满足” that are common discussion topics outside this specific persona skill. That can cause unintended activation and persona hijacking, where normal user requests are routed into this roleplay behavior without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the agent to answer in a fixed persona and expression style by default, which can override normal assistant behavior without the user's explicit consent. This creates response steering risk: benign requests may be reframed in a specific ideological or stylistic lens, reducing user autonomy and potentially conflicting with higher-priority system behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file is entirely presented in Chinese and describes the skill as suitable for delivery and use, but it does not indicate that language choice is optional or that the Chinese-only presentation is a documented regional constraint. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This markdown file is entirely written in Chinese and provides no indication that language selection is optional or that the locale constraint is required for a region-specific purpose. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions and research content exclusively in Chinese, and there is no indication that the language choice is optional or tied to a documented region-specific requirement. Under the natural-language policy rules, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains natural-language content exclusively in Chinese, and there is no indication that the language choice is optional, user-selected, or required for a documented region-specific purpose. Under the language/locale policy rule, forcing a single language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains natural-language content exclusively in Chinese, and there is no indication that the skill or document is intentionally limited to Chinese-speaking users or a China-specific compliance context. The policy requires flagging language or locale constraints when a specific language is forced without user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file is entirely written in Chinese and provides no indication that the language is optional, user-selected, or required for a documented region-specific purpose. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The title and the entire document are written exclusively in Chinese, and there is no indication that the skill or artifact is region-specific or that users may choose another language. Under the policy rule, natural-language content that enforces a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.