Security audit

KokoChat Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web-search wrapper that sends search queries to KokoChat's hosted endpoint, with no evidence of hidden persistence, local data collection, or destructive behavior.

Before installing, understand that your search terms will be sent to KokoChat's hosted search service at deeply.plus by default. Use it only for queries you are comfortable sharing with that service, and review any endpoint or token environment variables if you run a private deployment.

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
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 (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.
md
other search) API credentials; it only runs `bin/search.mjs`, which POSTs

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.
md
other search) API credentials; it only runs `bin/search.mjs`, which POSTs

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill explicitly requires network capability and exposes an executable wrapper, but the manifest does not declare a tighter tool scope such as permissions or allowed-tools. That increases the chance an agent or host grants broader execution/network access than intended, which matters here because the skill sends user-provided queries to a remote third-party endpoint.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases include very generic language such as 'search the web' and multilingual variants that are likely to appear in normal conversation. In an agent environment, overly broad triggers can cause the skill to activate unexpectedly and send user queries off-device to the hosted proxy without clear user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The input description says the query must be "concise English keywords," which is a natural-language locale constraint. The document does not offer an opt-in language choice or explain why English is required, so this appears to force a specific language policy on users.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.