Security audit

小红书爆款文案拆解

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports read-only social media research, with expected third-party data sharing and package-installation risks.

Use search terms and links you are comfortable sending to SocialDataX, and review complete returned URLs before sharing them. Keep the API key in supported secret storage. Prefer a reviewed, pinned CLI version: this review covers the supplied skill instructions, not the external package or future releases.

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium

Category: MCP Rug Pull
Confidence: 98% confidence
Finding: The search command uses npx -y socialdatax-skills@latest, allowing a changing npm release to execute without an installation confirmation. A compromised package release or dependency could run with the agent's permissions and access its API key and other accessible resources; the skill's read-only business operations do not constrain package execution.
Content: No source excerpt is available for this finding.

The workflow sends user-supplied search terms and note identifiers or links to SocialDataX without a privacy disclosure.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: The skill instructs the agent to execute API-backed searches and detail requests using user-provided inputs, which may include unpublished product directions or shared note links. Although SocialDataX is identified as the provider, the skill does not explicitly warn users that these inputs leave the agent environment and are transmitted to that third-party service.
Content: No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium

Category: MCP Rug Pull
Confidence: 98% confidence
Finding: The note-detail command executes the npm package through the mutable @latest tag with automatic confirmation. Although this is a direct CLI rather than an MCP server, the underlying supply-chain exposure is real: a compromised release could execute arbitrary code in the credential-bearing agent environment.
Content: No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium

Category: MCP Rug Pull
Confidence: 98% confidence
Finding: The URL-based detail command also retrieves and executes socialdatax-skills@latest without a fixed reviewed version. Its legitimate data-retrieval purpose does not prevent a future compromised release or dependency from accessing secrets or modifying files under the agent's permissions.
Content: No source excerpt is available for this finding.