Back to skill

Security audit

Google SERP Images Search API

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but its documented runner passes the Just Serp API key on the command line, which can expose the credential locally.

Review before installing. Use a restricted Just Serp API key if possible, avoid running the documented command in shared or heavily monitored environments, and rotate the key if it may have been exposed through process listings or command logging. Treat any raw HTML returned by the API as untrusted content.

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:334
Finding

API Key Exposed Through Command-Line Arguments

Content
View full analysis
"}' ``` The implementation requires and parses the key from that argument: ```js if (!args.apiKey) { fail("Missing required --api-key argument."); } const params = parseParams(args.paramsJson); applyDefaults(operation, params); validateRequired(operation, params); const baseUrl = manifest.baseUrl; const url = new URL(operation.path, ensureBaseUrl(baseUrl)); applyPathParams(operation, params, url); applyQueryParams(operation, params, url); const requestInit = { headers: { "accept": "application/json", "X-API-Key": args.apiKey, }, method: operation.method, }; ``` ```js function parseArgs(argv) { const parsed = { apiKey: null, operation: null, paramsJson: "{}" }; for (let index = 0; index < argv.length; index += 1) { const flag = argv[index]; const value = argv[index + 1]; if (flag === "--operation") { parsed.operation = value; index += 1; continue; } if (flag === "--params-json") { parsed.paramsJson = value; index += 1; continue; } if (flag === "--api-key") { parsed.apiKey = value; index += 1; continue; } fail(`Unknown argument "${flag}".`); } return parsed; } ``` ### Technical Analysis Shell expansion of `"$JUST_SERP_API_KEY"` places the secret in the Node process argument vector. Depending on operating-system process visibility, container configuration, monitoring software, shell auditing, and diagnostic tooling, command-line arguments may be exposed through process inspection facilities or c ...[truncated 1877 chars]
Remediation
View remediation
"}' ``` If the environment is already exported, omit the redundant inline assignment entirely. 5. For environments where environment-variable exposure is also a concern, support reading the key from standard input or a credential file with restrictive permissions. Do not print the value in errors, debug output, or telemetry. 6. Rotate any API key that may previously have been exposed through process listings or command-line logging. Apply server-side scope, quota, and expiration restrictions where supported. ]]>
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill instructs use of a network-capable helper (node .../bin/run.mjs) against an external API, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates a governance gap: an agent platform may permit broader tool or network use than intended, reducing isolation and making review and enforcement harder.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The operation explicitly supports returning raw HTML and allows SafeSearch to be turned off, but the documentation does not warn users about privacy, compliance, or exposure to adult or otherwise unsafe content. In an agent setting, this omission can lead to unsafe default use, accidental collection of sensitive page content, or downstream rendering/parsing of untrusted HTML without appropriate safeguards.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.