Back to skill

Security audit

presearch

Security checks for vulnerabilities and agentic risk

Overview

This is a small search API reference skill whose external query behavior is disclosed and aligned with its purpose.

Installers should understand that searches are sent to Presearch with a bearer API key. Do not include passwords, private prompts, customer data, or other sensitive material in search queries, and independently verify the provider's privacy claims and terms if they matter for your use case.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation clearly identifies a third-party search endpoint but does not warn users that their search queries will be transmitted off-platform to an external service. In an agent context, queries may contain sensitive user data, internal prompts, or proprietary information, so the lack of an explicit disclosure increases the risk of unintended data exfiltration and privacy violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Defaulting to en-US is not a direct security flaw, but it can silently influence how user input is processed and transmitted without clear user awareness or consent. In privacy-sensitive agent workflows, undocumented locale defaults can create mismatches with user expectations, affect search behavior, and contribute to unnecessary disclosure of inferred regional or language preferences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.