# Skill Security Audit

> Statically inspect third-party agent skills before installation for prompt injection, destructive commands, credential access, dependency risk, hidden network behavior, and unsafe permissions. Use before installing or publishing an unfamiliar skill.

- **Type:** Skill
- **Install:** `agentstack add skill-tikazi-tikaz-ai-skills-skill-security-audit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [TIKAZI](https://agentstack.voostack.com/s/tikazi)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [TIKAZI](https://github.com/TIKAZI)
- **Source:** https://github.com/TIKAZI/TIKAZ-AI-Skills/tree/main/suites/engineering/skill-security-audit
- **Website:** https://tikazi.github.io/TIKAZ-AI-Skills/

## Install

```sh
agentstack add skill-tikazi-tikaz-ai-skills-skill-security-audit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Skill Security Audit

This TIKAZ Edition is designed, integrated, refactored, and continuously maintained by **TIKAZ** as a suite safety gate. External scanners remain separately attributed when actually used.

Inspect `SKILL.md`, scripts, manifests, dependencies, assets, links, and install commands. Classify findings as blocker, high, medium, or informational and cite exact files and lines. Check for secret collection, browser/session access, recursive deletion, privilege escalation, remote execution, obfuscated payloads, unpinned dependencies, and instructions that override user intent.

Return a recommendation: `approve`, `approve-with-conditions`, or `reject`. Static approval is not a guarantee of safety; use least privilege during installation.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [TIKAZI](https://github.com/TIKAZI)
- **Source:** [TIKAZI/TIKAZ-AI-Skills](https://github.com/TIKAZI/TIKAZ-AI-Skills)
- **License:** MIT
- **Homepage:** https://tikazi.github.io/TIKAZ-AI-Skills/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-tikazi-tikaz-ai-skills-skill-security-audit
- Seller: https://agentstack.voostack.com/s/tikazi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.