Back to skill

Security audit

AI提示词变现

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a prompt-selling workflow, but it exposes real-looking platform credentials and tells an agent to read a separate secret file for automated logins.

Do not install or use this version unless the exposed credentials are removed and rotated. A safer version should use user-provided or managed secret handles, require explicit confirmation before login or posting, verify the exact platform domain before filling credentials, and add privacy/compliance guidance for any private-channel lead collection.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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

Error
Location
SKILL.md:64
Finding

Plaintext Platform Credentials Embedded in the Skill Definition

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:73
Finding

Broad External Secret-File Access and Automatic Credential Submission

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (18)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill embeds real-looking third-party platform credentials and instructs the agent to retrieve additional secrets from a separate secret file for automated login. This exceeds ordinary workflow documentation and creates a direct path to unauthorized account access, credential misuse, and secret exfiltration if the skill is invoked or copied.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The login table presents the credentials as part of a publishing workflow, but the values appear to be actual phone numbers and passwords rather than placeholders. Publishing real-looking credentials in a skill file risks immediate compromise of external accounts and encourages unsafe reuse of exposed secrets by downstream users or agents.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill directs automated login and credential autofill for third-party services without any user-facing disclosure, approval step, or warning about secret access. In context, this makes the workflow more dangerous because it normalizes silent credential handling for monetization tasks, increasing the chance of unauthorized publishing, account takeover, or inadvertent disclosure of stored secrets.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill content appears to require Chinese-language interaction, but it does not state that the skill is China-specific or offer the user an alternative language. Under the 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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt profile sets "Language: 中文" as a fixed requirement, which is a natural-language locale constraint. The file does not offer the user a language choice or explain why Chinese is required for a region-specific or compliance-related purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The embedded skill profile explicitly states "Language: 中文", which imposes a specific language preference. Under the policy, forced language or locale without user opt-in is a natural-language policy violation unless the constraint is clearly justified or optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt profile explicitly sets the skill language to Chinese with no indication that the user can choose another language. This is a natural-language policy concern because it imposes a specific locale/language by default rather than offering user opt-in or documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The guide explicitly instructs sellers to move users from the platform into private channels ('好评后引导私域') without any notice about privacy, record-keeping, fraud, or off-platform transaction risks. In a monetization workflow, this increases the chance of social engineering, unmonitored payment arrangements, and collection of personal contact data outside the platform's protections.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 小红书 guidance says to avoid mentioning direct purchase and instead direct users to private channels or 闲鱼, which is a deliberate off-platform diversion pattern. This is risky because it bypasses platform safeguards and can facilitate deceptive sales flows, privacy-invasive contact exchange, and reduced transparency for users.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The sample script asks users to add a private contact account ('可加V:XXX') without any caution about exposing personal contact information or moving outside monitored channels. In this skill's sales and lead-generation context, that language can be readily used for spam, phishing, or coercive upselling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script encourages users to continue the interaction via comments and private messages to obtain the product, again without any privacy or data-handling notice. Because the skill is specifically designed for monetization and traffic diversion, this context makes the finding more dangerous by operationalizing lead capture through less transparent channels.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all instructions and evaluation criteria exclusively in Chinese, and there is no indication that users may opt into another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The template specifies "Language: 中文" as a fixed default in natural-language instructions. This can violate language/locale policy because it forces a specific language without user opt-in, and the file does not indicate that the template is intentionally region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The profile explicitly sets "Language: 中文", which is a natural-language locale constraint. The file does not indicate that users can opt into another language or that this skill is intentionally limited to a Chinese-only regulatory or regional context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The profile declares "Language: [中文/英文]", which constrains the skill to specific languages but does not state that the user may choose their preferred language. Under the policy, forcing a language or locale without explicit 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
96% confidence
Finding

The prompt profile sets "Language: 中文" as a fixed requirement. This is a natural-language locale constraint, but the file does not indicate user opt-in or a region-specific justification for enforcing Chinese.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The prompt profile sets "Language: 中文" as a fixed requirement, which is a natural-language locale constraint. The file does not indicate that this is optional, user-selected, or justified as a region-specific skill, so it conflicts with the policy against forcing a specific language without opt-in.

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 only Chinese-language content and does not indicate that the skill or report is region-specific or that users may choose another language. Under the language/locale policy rule, forcing a single language without opt-in or justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.