# Adversarial Review

> Hostile Grok review that challenges design; web on by default

- **Type:** Skill
- **Install:** `agentstack add skill-sfourdrinier-grok-skills-adversarial-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [sfourdrinier](https://agentstack.voostack.com/s/sfourdrinier)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [sfourdrinier](https://github.com/sfourdrinier)
- **Source:** https://github.com/sfourdrinier/grok-skills/tree/main/plugin/skills/adversarial-review

## Install

```sh
agentstack add skill-sfourdrinier-grok-skills-adversarial-review
```

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

## About

## How to run (transparent)

1. Take the absolute **Base directory for this skill** from the Skill tool
   (the folder that contains this skill's `SKILL.md` and `run.mjs`).
2. Set `SKILL_BASE` to that path. Do **not** invent versioned cache paths.
3. Always invoke the companion **only** through this skill's runner:

```bash
SKILL_BASE=''
# Required for completion notifications (plugin/references/execution-context.md):
export GROK_COMPANION_EXECUTION_CONTEXT=foreground   # or background
node "$SKILL_BASE/run.mjs"  [args...]
```

`run.mjs` finds the plugin install from its own location and runs
`scripts/grok-companion.mjs`. No `CLAUDE_PLUGIN_ROOT` / `PLUGIN_ROOT` required.

If the host already exported `CLAUDE_PLUGIN_ROOT` or `PLUGIN_ROOT`, you may call
`node "$CLAUDE_PLUGIN_ROOT/scripts/grok-companion.mjs"` instead; prefer
`"$SKILL_BASE/run.mjs"` whenever the Skill tool loaded this skill.

Return companion **stdout verbatim**. Never put free-text in `--task "..."`;
use `--task-file -` with a single-quoted heredoc.

## Command

Never `--task "..."`. Example:

```bash
export GROK_COMPANION_EXECUTION_CONTEXT=foreground
node "$SKILL_BASE/run.mjs" adversarial-review [flags from $ARGUMENTS, values single-quoted] --task-file - 
GROK_TASK
```

Return the envelope verbatim.

## Source & license

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

- **Author:** [sfourdrinier](https://github.com/sfourdrinier)
- **Source:** [sfourdrinier/grok-skills](https://github.com/sfourdrinier/grok-skills)
- **License:** MIT

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-sfourdrinier-grok-skills-adversarial-review
- Seller: https://agentstack.voostack.com/s/sfourdrinier
- 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%.