Back to skill

Security audit

IMDb Recommendations API

Security checks for vulnerabilities and agentic risk

Overview

The skill is narrowly scoped to IMDb recommendation lookups, but it handles the API token in a way that can leak it through command metadata or request URLs.

Review this before installing if the JustOneAPI token has billing impact or broad account access. Prefer a limited, easily rotated token, avoid command/request tracing, and rotate the token if it may have appeared in process logs, shell history, proxy logs, or server logs.

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:216
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 query parameters, including the token, are appended to the 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 also instructs users to place the token in process arguments: ```bash node {baseDir}/bin/run.mjs --operation "titleMoreLikeThisQuery" --token "$JUST_ONE_API_TOKEN" --params-json '{"id":""}' ``` ### Technical Analysis The credential is exposed through two separate metadata channels: 1. Passing the token through `--token` places it in the process argument vector. Depending on operating-system configuration and exec ...[truncated 2348 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes a network-capable helper (node {baseDir}/bin/run.mjs) and is explicitly designed to call an external API, but it does not declare any tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can allow broader-than-expected outbound access at runtime, reducing transparency for reviewers and increasing the blast radius if the skill or its wrapper is modified or abused.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill requires the authentication token to be sent as a query parameter and automatically injects it into the request URL. Query-string credentials are commonly exposed through logs, browser/history systems, reverse proxies, monitoring tools, and error telemetry, which increases the chance of credential disclosure even when HTTPS is used.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The API design requires the user's authentication token to be sent in the URL query string, which is routinely exposed in browser history, proxy/server logs, monitoring tools, referrer headers, and error telemetry. Even over HTTPS, query parameters are more broadly propagated than headers, so this increases the chance of credential leakage and subsequent unauthorized API access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The API design requires the authentication token to be sent as a query parameter, which is commonly exposed in browser history, proxy logs, analytics systems, server access logs, and referrer headers. Because this skill documents the token in the URL without any warning or safer alternative, it increases the chance of credential leakage and unauthorized API use.

Content

No source excerpt is available for this finding.