Security audit

潜在意向筛选虾

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent lead-screening tool, but it handles social comments and private messages for sales follow-up with weak consent and privacy safeguards.

Review this skill before installing if you will use it on private messages or customer data. Only run it on data you are authorized to process, confirm recipients before pushing leads to Feishu or sales teams, and consider redacting personal details that are not needed for follow-up.

A.I.G

Vulnerability Patterns

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

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill explicitly supports analyzing private messages and public comments to score purchase intent, then forwarding high-intent leads to sales teams or Feishu, but it does not require a clear user-facing consent, legality, or disclosure check before downstream sharing. In this context, the combination of surveillance-style profiling, private-message processing, and automatic lead transfer materially increases privacy, compliance, and misuse risk.
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, common phrases such as ‘求推荐’, ‘求链接’, and other generic sales/interest terms that can match many benign user requests. This raises the chance of unintended activation, causing the skill to process unrelated conversations and potentially handle sensitive comment or message data in contexts where the user did not intend to invoke lead-mining behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown file presents all skill content in a single language and does not indicate that Chinese is optional, configurable, or required for a region-specific use case. Under the language/locale 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

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The file is entirely written as mandatory Chinese-language semantic rules and does not indicate that language selection is optional or configurable. Under the policy, forcing a specific language or locale 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: 88% confidence
Finding: This file’s natural-language content is fully constrained to Chinese, from the title through all scoring guidance and message templates. Under the stated policy, forcing a specific language without user opt-in is a reportable natural-language policy issue unless the locale restriction is clearly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The header comments, usage text, commands, examples, and status messages are all presented only in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the restriction is explicitly justified or alternatives are offered.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.