Security audit

Douyin Creator Marketplace (Xingtu) KOL Keyword Search API

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to call the advertised JustOneAPI endpoint, but it handles the API token in ways that can expose it through process listings or URL logs.

Review this before installing if your JustOneAPI token has paid quota, broad account access, or long lifetime. Use a narrowly scoped or disposable token if possible, avoid sharing logs or process listings from runs, and rotate the token if you suspect command history, monitoring, or URL logs captured it.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: bin/run.mjs:19
Finding: API Token Exposed Through Process Arguments and URL Query Parameters
Content: View full analysis
parameter.name === "token"); if (!tokenParam || params.token !== undefined) { return; } if (!cliToken) { fail("--token is required for this operation.", { operationId: operation.operationId, }); } params.token = cliToken; } ``` All parameters marked as query parameters, including `token`, are appended to the request URL: ```js function applyQueryParams(operation, params, url) { for (const parameter of operation.parameters.filter((item) => item.location === "query")) { const value = params[parameter.name]; if (value === undefined) { continue; } appendValue(url.searchParams, parameter.name, value); } } ``` The documented invocation explicitly places the environment variable value in a command-line argument: ```bash node {baseDir}/bin/run.mjs --operation "searchKolSimpleV1" --token "$JUST_ONE_API_TOKEN" --params-json '{"keyword":"","platformSource":"_1","page":1}' ``` ### Technical Anal ...[truncated 2946 chars]
Remediation: View remediation

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 (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill invokes a network-capable helper (node .../bin/run.mjs) and is designed to call an external API, but it does not declare an explicit tool scope such as permissions or allowed-tools. This can weaken enforcement and review boundaries in agent runtimes, increasing the risk of unintended or overly broad outbound network access under the guise of a narrowly scoped API skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Passing a sensitive authentication token in the URL query string is dangerous because query parameters are commonly logged by clients, proxies, gateways, browser history, analytics tools, and server access logs. Even over HTTPS, the token may be exposed through operational telemetry or accidental sharing, increasing the risk of credential leakage and unauthorized API access.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This is a manifest file, so vague-trigger review applies. The description and display name explain what the skill does, but they do not define how or when it should be invoked, nor do they provide boundaries or negative examples, which can make activation overly broad in systems that infer invocation from manifest text.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.