Security Audit

james-katz/zkool_skill:root

github.com/james-katz/zkool_skill

AI SkillCommit 4400413a06c3

CRITICAL

Scanned 8 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

james-katz/zkool_skill:root received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 8 findings: 4 critical, 1 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Arbitrary command execution, Remote code execution: curl/wget pipe to shell.

The analysis covered 4 layers: llm_behavioral_safety, manifest_analysis, static_code_analysis, dependency_graph. The manifest_analysis layer scored lowest at 40/100, indicating areas for improvement.

Last analyzed on February 11, 2026 (commit 4400413a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

40%

Static Code Analysis

63%

Dependency Graph

91%

LLM Behavioral Safety

55%

Behavioral Risk Signals

Network Access

3 findings

Filesystem Write

1 finding

Shell Execution

4 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings8

Severity	Finding	Layer	Location
CRITICAL	Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Unknown	/tmp/skillscan-clone-ni_bgihk/repo/scripts/zkool_cli.js:14
CRITICAL	Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands.	Unknown	/tmp/skillscan-clone-ni_bgihk/repo/SKILL.md:44
CRITICAL	Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter.	Unknown	/tmp/skillscan-clone-ni_bgihk/repo/SKILL.md:44
CRITICAL	Unverified Third-Party Repository for Wallet Binary The skill instructions direct the user to clone and compile a binary from `https://github.com/hhanh00/zkool2.git`. This appears to be a personal, unverified repository rather than an official Zcash or recognized organization repository. As this binary (`zkool_graphql`) manages private keys and financial transactions, relying on an arbitrary GitHub user's repository poses a critical supply chain risk of backdoors or malicious code. Use an official Zcash repository or a verified fork. Pin the dependency to a specific commit hash rather than the main branch to ensure reproducibility and prevent upstream changes from introducing malware.	Unknown	SKILL.md:56
HIGH	Unrestricted Access to Wallet Seed Phrase The `zkool_cli.js` script uses dynamic method dispatch to execute any method on the `ZkoolClient` class based on input arguments. The class includes `getAccountSeed`, which returns the plaintext seed phrase. This allows the AI agent (or an attacker via prompt injection) to retrieve and dump the private keys to the conversation logs/stdout. Implement a strict allowlist of safe methods in `zkool_cli.js`. Explicitly exclude sensitive methods like `getAccountSeed` from the CLI wrapper unless there is a specific, secured workflow for them.	Unknown	scripts/zkool_cli.js:33
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Unknown	/tmp/skillscan-clone-ni_bgihk/repo/SKILL.md:48
MEDIUM	Unpinned npm dependency version Dependency 'dotenv' is not pinned to an exact version ('^16.4.7'). Pin dependencies to exact versions to reduce drift and supply-chain risk.	Unknown	/tmp/skillscan-clone-ni_bgihk/repo/package.json
LOW	Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution.	Unknown	/tmp/skillscan-clone-ni_bgihk/repo/package.json

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e4d051d050439f01.svg)](https://skillshield.io/report/e4d051d050439f01)