Back to skill

Security audit

skill for searching images and boards in zizo library (https://zizo.pro).

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Zizo search skill that sends search queries with a user-provided token to a configured HTTPS Zizo server; no hidden persistence or destructive behavior was found.

Install only if you intend to use Zizo for image and board search. Keep ZIZO_TOKEN private, leave ZIZO_SERVER at the default unless you trust the alternate server, and remember that generic image-search prompts may be routed to Zizo by this skill.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (14)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

md
- `node dist/index.js version` to verify installation

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest says to use the skill when a user asks to search for images, photos, pictures, visual assets, or boards/collections, which is a wide set of everyday phrases without explicit boundaries or exclusion conditions. Because it does not clearly define when this skill should be preferred over other generic search or media tools, it could be invoked unintentionally.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code sends user search queries and a bearer token to a remote server over HTTPS without any explicit disclosure, consent flow, or code-level restriction on the destination beyond requiring HTTPS. Because ZIZO_SERVER is environment-configurable, a misconfigured or malicious deployment could route sensitive queries and credentials to an unintended host, increasing the risk of data exposure and token compromise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The configuration instructions are written in Chinese while the rest of the document is mixed-language, and there is no statement that the user can choose their preferred language. This can conflict with language/locale policy expectations when a skill imposes a language format without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

Multiple comments and labels are written in Chinese, which indicates a language-specific presentation without any visible opt-in or justification for a locale restriction. Under the stated policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest frames this skill as a search tool for images and boards, but the implementation also reads server, token, and default settings directly from environment variables. While the network search itself is expected, environment-variable access for credentials/config is an additional capability not justified by the manifest's narrow user-facing description.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 22)May include surrounding context.

json
"author": "",
  "license": "MIT",
  "devDependencies": {
    "@vercel/ncc": "^0.38.3"
  },
  "engines": {
    "node": ">=16.0.0"