Security audit

小红书评论分析

Security checks for vulnerabilities and agentic risk

Overview

This skill sends user-provided Xiaohongshu links to an AI Skills API for comment analysis, with no evidence of hidden local access, persistence, or destructive behavior.

Install this only if you are comfortable sending Xiaohongshu links, parsed note metadata, and related analysis requests to the AI Skills service using your API key. Review or control AISKILLS_BASE_URL if set, because it determines where requests and the API key are sent.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill declares required environment variables and describes networked task creation/polling, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates a transparency and governance gap: runners and reviewers cannot easily constrain or audit the skill's access to secrets and outbound network use, increasing the chance of overprivileged execution or unintended data exfiltration paths.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill asks users to provide Xiaohongshu links and analyzes associated comments, but the description does not clearly disclose that this content and related data will be sent to an external API service. This is dangerous because users may unknowingly transmit third-party content, comment text, or potentially sensitive business analysis targets to an external processor without informed consent or appropriate compliance review.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The display name, short description, and default prompt are entirely in Chinese and indicate a Chinese-language operating context, but the file provides no user opt-in or alternative language choice. Per the policy, forcing a specific language or locale without user choice is 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: 95% confidence
Finding: The natural-language strings in the schema are entirely in Chinese, which imposes a specific language/locale on users without offering an alternative or documenting that the skill is intentionally region-specific. This matches the language/locale policy concern for files of any type when a specific language is forced without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The primary user-facing question and skill name are entirely in Chinese, which suggests the skill is oriented to a single language. The file does not state that this is an opt-in locale-specific skill or offer language choice, creating a potential language-policy violation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This manifest defines the invocation only as "comment-analysis-task" without any natural-language constraints, explicit trigger phrases, or exclusion conditions. Because this is a manifest file, the lack of specificity can make it unclear when this skill should activate versus other comment-analysis skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The natural-language instructions and description are fully Chinese, which can amount to forcing a specific language without user opt-in under the stated policy. There is no note indicating that the skill is region-specific or that users may choose another language.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This manifest-style schema only says to paste a '小红书分享链接' without clarifying whether other URL forms are allowed, whether notes vs. videos differ, or providing exclusion examples. For manifest/config files, this kind of underspecified trigger/input scope can cause unintended or confusing activation/use because the accepted input boundaries are not explicit.
Content: No source excerpt is available for this finding.