Back to skill

Security audit

挖券券儿

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a real coupon-link helper, but broad auto-triggers and loose redirect/link handling warrant review before installing.

Install only if you are comfortable with a Chinese coupon skill contacting waquanquaner.cn and showing links supplied by that service. Treat returned links as third-party promotional content, avoid ambiguous auto-trigger use, and prefer a pinned or organization-approved installer path.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/query.js:18
Finding

Unrestricted Redirects and Untrusted API Content in Trusted Agent Output

Content
View full analysis
{ let parsedUrl; try { parsedUrl = new URL(urlStr); } catch (e) { return reject(new Error('无效的 URL: ' + urlStr)); } const client = parsedUrl.protocol === 'https:' ? https : http; const req = client.get(urlStr, { timeout }, (res) => { // 处理重定向 if (res.statusCode >= 300 && res.statusCode < 400 && res.headers.location) { return httpGet(res.headers.location, timeout).then(resolve).catch(reject); } let data = ''; res.on('data', chunk => data += chunk); res.on('end', () => { try { const json = JSON.parse(data); if (res.statusCode >= 400) { reject(new Error('API 返回错误 ' + res.statusCode + ': ' + (json.message || data.substring(0, 200)))); } else { resolve(json); } } catch (e) { reject(new Error('JSON 解析失败: ' + e.message)); } }); }); req.on('error', reject); req.on('timeout', () => { req.destroy(); reject(new Error('请求超时 (' + timeout + 'ms)')); }); }); } ``` From `scripts/query.js:65-83`: ```js async function fetchCompact(options = {}) { const apiUrl = options.compactApiUrl || config.COMPACT_API_URL; try { const response = await httpGet(apiUrl); // 验证核心字段 if (response && response.landing && response.landing.url) { return { success: true, compact: { channel: response.channel || 'skill_compact', date: response.date | ...[truncated 4513 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
README.md:17
Finding

Unpinned Package Execution Through the Documented npx Installation Command

Content
View full analysis
Remediation
View remediation
install waquanquaner`. 2. Where supported, use a lockfile, integrity hash, signed release, or verified artifact to bind installation to known content. 3. Prefer invoking a separately installed and organization-approved `clawhub` binary rather than allowing `npx` to download and immediately execute a package. 4. Document the expected package publisher, version, checksum, and registry source. 5. Recommend installation under a non-privileged account and advise users not to run the command with `sudo` or administrator rights. 6. Periodically review and update the pinned version rather than relying on an implicitly current release. ]]>
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (11)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README advertises broad natural-language triggers such as '外卖红包', '饿了么优惠', and '领券' for automatic activation. Overly generic triggers can cause the skill to run in unrelated conversations, leading the agent to make external network requests or inject promotional links when the user did not clearly ask for this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The invocation examples include ambiguous everyday phrases like '今天吃什么' and '点外卖怎么省钱', which are common conversational prompts not necessarily intended to authorize this specific skill. In an agent context, such examples encourage unsafe auto-invocation and can trigger unsolicited outbound requests to the remote coupon service or present third-party links without informed user intent.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill’s metadata and documentation promise concrete coupon discovery and redemption across multiple food-delivery platforms, but the file provides only marketing claims and routes users to an external site/tooling without demonstrating the stated functionality. This is dangerous because users may be induced to trust and invoke a third-party service under false pretenses, increasing phishing, deceptive redirection, or unwanted data exposure risk.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes broad, everyday phrases such as '今天吃什么' and '点外卖', making accidental invocation likely in normal conversation. This can cause the agent to contact the external coupon service unexpectedly, exposing user intent/context and creating unnecessary interaction with an untrusted third-party domain.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The installation command uses npx clawhub without pinning a specific version, so users may fetch and execute whatever package version is current at install time. This creates a supply-chain risk: a compromised publisher account, malicious update, or breaking change could cause arbitrary code execution on the installing machine or agent environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file uses Chinese-only labels, comments, trigger phrases, and platform names throughout, and does not indicate that the skill is limited to Chinese-speaking users or offer any language/locale opt-in. Under the policy, forcing a specific language without user choice can be a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code file contains natural-language descriptions and user-facing output exclusively in Chinese, including the module header and CLI messages. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This JavaScript file is a code file, so SQP-3 applies. The natural-language descriptions and examples are entirely Chinese and the parser logic is explicitly designed around Chinese trigger phrases, but there is no indication of user opt-in, alternative locale support, or documented justification for restricting the skill to Chinese input.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The display name and description are presented only in Chinese, which indicates a language-specific experience with no visible opt-in or alternative locale. Under the policy rule for natural-language violations, forcing a specific language without user choice can be a locale-policy issue unless it is explicitly documented as region-specific and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The function explicitly formats dates using the 'zh-CN' locale and the surrounding strings are fixed in Chinese, which enforces a specific language/locale in output. The policy allows locale constraints only when user choice or clear justification is provided, neither of which appears in this file.

Content

No source excerpt is available for this finding.