Security audit

X / Twitter 数据助手 SocialDataX

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports read-only X/Twitter research through SocialDataX, with ordinary privacy, API-credit, and software-dependency risks.

Search terms, identifiers, URLs, and pasted share text are supplied to SocialDataX, and requests may consume credits. Avoid confidential inputs and protect your API key. Prefer a reviewed, pinned package version and limit its access to unrelated files and secrets. The referenced npm release was not independently verified.

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 (19)

The instructed API searches and lookups lack a privacy warning that user-supplied inputs are sent to SocialDataX.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: The workflow instructs the agent to run searches and lookups with user-supplied keywords, post URLs, or share text through the SocialDataX service, but does not warn that these inputs leave the user's environment. The read-only safety statement addresses account modifications and credential storage, not disclosure of potentially sensitive research queries or pasted text to a third party.
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: 99% confidence
Finding: The command executes socialdatax-skills@latest, allowing a mutable npm release to run without a version review or interactive installation confirmation. A compromised release could access SOCIALDATAX_API_KEY and other resources available to the agent; the documented read-only API purpose does not constrain local package execution.
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: 99% confidence
Finding: This paginated search example executes the mutable @latest package through npx -y. A compromised future release could execute arbitrary code with the agent's permissions and access its API key; this repeats the same supply-chain issue as line 29.
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: 99% confidence
Finding: The detail command runs socialdatax-skills@latest rather than an immutable reviewed release. Package compromise could expose the runtime API key or local resources, regardless of the intended read-only lookup operation.
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: 99% confidence
Finding: This URL-based detail example automatically executes a mutable npm release. If that release is compromised, it can run with the agent's permissions and access SOCIALDATAX_API_KEY; accepting a post URL does not limit package privileges.
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: 99% confidence
Finding: The comments command executes @latest with automatic installation confirmation. A malicious replacement release could access local data and credentials, making this another occurrence of the same unpinned-execution weakness.
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: 99% confidence
Finding: This comments lookup executes a package selected by the mutable @latest tag. A compromised release could run arbitrary code in the agent's environment, including accessing the API key supplied for legitimate data calls.
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: 99% confidence
Finding: The replies example executes an unpinned package through npx -y. A compromised npm release could act beyond reply retrieval and access agent-readable files or secrets.
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: 99% confidence
Finding: The user-info command resolves and executes the mutable @latest release. A compromised release would inherit the agent's permissions and API credential, despite the command's read-only business purpose.
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: 99% confidence
Finding: This username lookup executes socialdatax-skills@latest without fixing the reviewed code version. An attacker controlling a later release could execute code with the agent's privileges and steal its API key.
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: 99% confidence
Finding: This profile lookup automatically runs a package selected by a mutable npm tag. Package compromise could expose local resources and credentials; the supplied profile URL does not constrain what the executable can do.
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: 99% confidence
Finding: The user-posts example executes the mutable @latest package with npx -y. A compromised release could perform arbitrary local actions using the agent's permissions rather than merely retrieve posts.
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: 99% confidence
Finding: This creator-post lookup runs an unpinned npm release automatically. If the package distribution is compromised, the executable can access the runtime API key and other agent-accessible resources.
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: 99% confidence
Finding: The profile-based user-posts command executes socialdatax-skills@latest. This mutable dependency creates a supply-chain execution risk, with potential credential theft or local compromise if a future release is malicious.
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: 99% confidence
Finding: The all-posts example automatically executes a mutable @latest release. Its pagination option is not the root vulnerability; the risk is running potentially changed package code with access to the agent's credentials and 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: 99% confidence
Finding: This creator-replies command executes the unpinned @latest package. A compromised release could access local files or exfiltrate the API credential even though the documented operation only retrieves replies.
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: 99% confidence
Finding: The username-based replies example automatically runs code selected by a mutable npm tag. A malicious release could execute with the agent's privileges and access SOCIALDATAX_API_KEY.
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: 99% confidence
Finding: The profile-based replies command executes socialdatax-skills@latest with automatic installation confirmation. This repeats the same supply-chain weakness: a compromised release could access the agent's runtime secrets and local resources.
Content: No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx availability'.

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.