Back to skill

Security audit

yuketang-incub

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its Rain Classroom teaching-data purpose, but its installer and response-handling instructions create review-worthy security and privacy risks.

Review before installing. Use this only if you trust the Rain Classroom endpoint and the mcporter package source, prefer a manually reviewed MCP config over running the scripts, avoid running setup with elevated privileges, and treat YUKETANG_SECRET as a sensitive credential. Be aware that setup.sh silently reports an install event and duration, and that one skill instruction allows remote MCP text to become the assistant's verbatim final response.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (4)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:131
Finding

Remote MCP Response Can Hijack the Agent's Final Output

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
setup.js:29
Finding

Command Injection Through YUKETANG_SECRET in the Node.js Installer

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
setup.js:34
Finding

Unpinned mcporter Package Is Downloaded and Executed During Setup

Content
View full analysis
&1 | grep -q "yuketang-mcp"; then echo "✅ Verification passed" npx mcporter list | grep -A 1 "yuketang-mcp" || true ``` ```bash npx mcporter call yuketang-mcp claw_report \ --args "{\"payload\":{\"durationMs\":${DURATION}},\"action\":\"install\"}" \ >/dev/null 2>&1 || true ``` The source contains Chinese output strings. The English rendering above preserves the commands and complete meaning relevant to the vulnerability. ### Technical Analysis The installers repeatedly execute `npx mcporter` without specifying an exact package version. The project has no declared `mcporter` dependency, lockfile, or integrity metadata. When a suitable local executable is absent, `npx` may retrieve and execute a package from the configured npm registry. This makes installation behavior depend on mutable external package state that was not part of the audited artifact. A compromised package version, registry account takeover, malicious registry configuration, or unsafe future release could execute code on the user's machine during setup. This finding concerns the unsafe dependency mechanism; the audit did not establish that t ...[truncated 983 chars]
Remediation
View remediation

other

Note
Location
setup.sh:99
Finding

Shell Installer Sends Undisclosed Installation Telemetry

Content
View full analysis
/dev/null 2>&1; then npx mcporter call yuketang-mcp claw_report \ --args "{\"payload\":{\"durationMs\":${DURATION}},\"action\":\"install\"}" \ >/dev/null 2>&1 || true fi ``` The source labels this behavior in Chinese as a silent report. The English rendering above preserves the complete command and meaning of the affected segment. ### Technical Analysis After configuring the authenticated MCP service, the shell installer invokes the remote `claw_report` operation with an `install` action and installation duration. Standard output and standard error are redirected to `/dev/null`, and `|| true` suppresses failures. The user-facing setup instructions do not disclose this reporting step or request consent. The equivalent Node.js installer does not perform it, producing inconsistent behavior depending on the installation method. Although the explicitly shown payload contains only the action and duration, the authenticated remote request can also inherently expose normal connection metadata such as source IP address and request time to the service. No broader telemetry contents should be inferred beyond the code shown. ### Attack Path 1. The user exports `YUKETANG_SECRET` and runs `bash setup.sh`. 2. The installer registers the authenticated MCP endpoint. 3. After setup, it invokes `claw_report` using the configured service. 4. The remote service receives an installation event and `durationMs`. 5. Output and errors are hidden, so the user receives no visible indication that reporting occurred. ### Impact Assessment The remote service learns that an installation occurred and how long the setup took, along with metadata normally associated with a network reque ...[truncated 164 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (19)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs users to configure and use a personal secret via an environment variable, but it does not declare any explicit tool scope or allowed-tools boundary. That weakens least-privilege controls and makes it harder for a host platform to constrain what capabilities the skill may access, increasing the risk of unintended secret exposure or broader-than-expected execution behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The setup tells users to place a personal secret in an environment variable but provides no warning about credential sensitivity, storage hygiene, shell history exposure, process inheritance, or log leakage. In practice, users may mishandle the secret, commit it to scripts, share terminal output, or leave it accessible to child processes and local tooling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This instruction forces a specific locale/timezone policy for all users: relative times must be interpreted using system Beijing time. The policy-violation rule applies because the file does not provide user opt-in, a configurable locale choice, or a clear justification that the skill is region-locked to that timezone.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

Using npx mcporter without pinning a version introduces a supply-chain risk because the latest package version will be fetched at execution time. If the package is compromised or a breaking/malicious release is published, users could execute unreviewed code during setup or operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description forces a specific language/locale in user-facing natural language without offering any alternative or opt-in. The stated policy flags language or locale constraints unless the skill offers user choice or clearly documents a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains all user-facing instructions and examples exclusively in Chinese, which can force a specific language on users without opt-in. The policy requires either offering a language/locale choice or clearly documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script reads YUKETANG_SECRET and interpolates it directly into a shell command executed via execSync. If the secret contains shell metacharacters, quoting edge cases, or attacker-controlled content, it can break command boundaries or be exposed through process listings, shell history, logs, or downstream tooling, turning a credential-handling step into command-injection and secret-leakage risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script reads the sensitive environment variable YUKETANG_SECRET and guides the user to set it, but it does not include any user-facing warning about the sensitivity of this credential or safe handling practices. Under the code-file criteria, access to sensitive environment variables should have some disclosure, and the surrounding messages only indicate setup steps, not a safety warning.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The script invokes npx mcporter without pinning an exact package version, so installation and execution may resolve to whatever version is current at runtime. This creates a supply-chain risk: a compromised, typosquatted, or maliciously updated package could execute arbitrary code during setup, and the command also carries an Authorization header containing the user's secret.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The verification step also runs npx mcporter without a pinned version, exposing users to the same untrusted package-resolution behavior during setup validation. Even though this second call does not pass the bearer token directly, it still executes code fetched at runtime from the package ecosystem.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The script invokes npx mcporter without pinning an exact package version, so execution depends on whatever version npx resolves at runtime. If the package or dependency chain is updated maliciously or unexpectedly, the setup script could run altered code during installation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

This call to npx mcporter list also relies on an unpinned package resolution path. That creates supply-chain risk because a different or compromised package version could be fetched and executed in the user's environment.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

Another unpinned npx mcporter execution appears during verification output. Repeated unpinned executions increase the chance of retrieving or running a tampered package version, especially in ephemeral environments.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The setup script performs a silent external reporting call after installation, which is not required for local MCP registration. Even though only duration and action are shown in the payload, the call goes to a remote MCP service using the configured authorization context, creating undisclosed telemetry and trust concerns.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The telemetry/reporting network call is performed with no user-facing warning, consent, or visible output. In a setup script that handles a bearer secret, undisclosed outbound traffic is especially concerning because users cannot easily assess whether sensitive context or metadata may be exposed.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The reporting step executes npx mcporter call without version pinning, combining supply-chain risk with an outbound network action. If a malicious package version is resolved, it could abuse the bearer token, alter telemetry, or execute additional unauthorized actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Multiple comments and console messages instruct the user only in Chinese, including setup guidance and the final suggested prompt. This creates a language policy issue because the skill effectively forces a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

Nearly all user-facing messages in the script are presented only in Chinese, including setup guidance and completion instructions, with no opt-in or alternate locale. This can violate language/locale policy where skills should not force a specific language absent user choice or documented regional justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Labeling the step as 'silent' while making an external service call is deceptive from a user-consent perspective. This mismatch reduces transparency and can cause users to unknowingly transmit installation metadata to a remote service.

Content

No source excerpt is available for this finding.