ClawHub
Back to skill

Security audit

serper-search

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Serper.dev Google Search plugin whose external search behavior is disclosed and aligned with its purpose.

Install only if you are comfortable sending search queries to Serper.dev/Google-backed search infrastructure and providing a Serper API key. Avoid using the tool for secrets, private customer data, credentials, or sensitive internal project names, and keep Clawdbot and dependencies updated.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly brokers user search queries to the external Serper.dev service, but the description does not clearly warn users that their prompts or search terms leave the local agent environment and are transmitted to a third party. This creates a privacy and data-handling risk because users may submit sensitive, proprietary, or regulated information under the assumption that the search is purely local or first-party.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The tool sends user-provided search queries directly to the external Serper API, which can expose sensitive prompts, internal project names, credentials accidentally included in queries, or other private user data to a third party. In an agent/tooling context this is meaningful because users or upstream agents may not realize their input is leaving the local trust boundary, and the code provides no disclosure, consent, or filtering before transmission.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The dependency uses a caret range (^0.32.0), which allows installation of newer compatible releases rather than a single audited version. That weakens build reproducibility and can unintentionally introduce a compromised or breaking upstream package through dependency drift or supply-chain compromise.

Content

Scanner excerpt · package.json (reported line 10)May include surrounding context.

json
"extensions": ["./index.ts"]
  },
  "dependencies": {
    "@sinclair/typebox": "^0.32.0"
  },
  "peerDependencies": {
    "clawdbot": ">=2026.1.24"

Unverifiable Dependency: clawdbot has 11 known advisory(ies) (CVE-2026-26317 (OpenClaw affected by cross-site request forgery (CSRF) through loopback browser ); GHSA-chm2-m3w2-wcxm (OpenClaw Google Chat spoofing access with allowlist authorized mutable email pri); CVE-2026-26328 (OpenClaw iMessage group allowlist authorization inherited DM pairing-store ident) +8 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
88% confidence
Finding

The peer dependency on clawdbot is specified as a broad minimum version (>=2026.1.24), so consumers may install vulnerable releases and the manifest gives no assurance that known advisories are excluded. Because the vulnerable package is not pinned or constrained to patched versions, security posture depends on the external environment rather than the skill itself.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
index.ts:72