ktg-plugin-marketplace/plugins/llm-security/commands/red-team.md

---
name: llm-security:red-team
description: Attack simulation — test hook defenses with crafted payloads
allowed-tools: Bash, Read
model: sonnet
---

# Red Team — Attack Simulation

Run crafted attack payloads against the plugin's own hooks to verify defenses.

## What was requested

The user ran `/security red-team` to test their hook defenses.

## Arguments

Parse `$ARGUMENTS` for:
- `--category <name>` — filter: secrets, destructive, supply-chain, prompt-injection, pathguard, mcp-output, session-trifecta, hybrid, unicode-evasion, bash-evasion, hitl-traps, long-horizon, all
- `--json` — raw JSON output
- `--adaptive` — mutation-based evasion testing (5 mutation rounds per passing scenario)

Default: all categories, fixed mode.

## Steps

1. **Run the attack simulator:**

```
node scanners/attack-simulator.mjs [--category <name>] [--verbose] [--adaptive]
```

The simulator runs 64 attack scenarios across 12 categories against the plugin's hooks. Each scenario sends a crafted payload and verifies the hook blocks or detects it.

In **adaptive mode** (`--adaptive`), for each scenario that passes (attack blocked), the simulator applies 5 mutation rounds:
1. Homoglyph substitution (Latin chars replaced with Cyrillic lookalikes)
2. Encoding wrapping (URL-encoded keywords)
3. Zero-width character injection (ZW chars inserted between keyword letters)
4. Case alternation (aLtErNaTiNg case)
5. Synonym substitution (keyword replacement from synonym table)

Bypasses are reported as findings but not auto-fixed.

2. **Present the results as a narrative report:**

For each category, explain:
- What was tested (the attack type)
- How many attacks were blocked
- Whether defenses are adequate

If any scenarios fail, explain the gap and what hook needs attention.

In adaptive mode, also explain:
- How many mutations were tested
- Which mutations found bypasses
- That bypasses are expected for synonym and encoding mutations (deterministic hooks cannot catch all evasions)

3. **Defense Score interpretation:**
- **100%** — All hooks functioning correctly. No defense gaps.
- **90-99%** — Minor gaps. Review failed scenarios.
- **Below 90%** — Significant gaps. Hooks may be misconfigured or missing.

## Categories

| Category | Hook Tested | Scenarios |
|----------|------------|-----------|
| secrets | pre-edit-secrets.mjs | 7 secret types (AWS, GitHub, PEM, DB, Bearer, Azure, Slack) |
| destructive | pre-bash-destructive.mjs | 8 commands (rm -rf, chmod 777, curl\|bash, fork bomb, mkfs, dd, eval) |
| supply-chain | pre-install-supply-chain.mjs | 4 managers (npm, pip, cargo, gem) |
| prompt-injection | pre-prompt-inject-scan.mjs | 6 patterns (override, spoofed headers, identity, evasion) |
| pathguard | pre-write-pathguard.mjs | 6 paths (.env, .ssh, .aws, .npmrc, /etc, hooks) |
| mcp-output | post-mcp-verify.mjs | 4 threats (injection, secrets, HTML traps, MCP injection) |
| session-trifecta | post-session-guard.mjs | 3 patterns (classic trifecta, MCP-concentrated, volume) |
| hybrid | post-mcp-verify.mjs | 8 patterns (P2SQL, recursive injection, XSS variants) |
| unicode-evasion | pre-prompt-inject-scan.mjs | 6 patterns (Unicode Tags, ZW chars, homoglyphs, BIDI, HTML entities, multi-lang) |
| bash-evasion | pre-bash-destructive.mjs | 5 patterns (empty quotes, dollar expansion, backslash splitting, supply chain) |
| hitl-traps | post-mcp-verify.mjs | 4 patterns (approval urgency, summary suppression, scope minimization, cognitive load) |
| long-horizon | post-session-guard.mjs | 3 patterns (delegation-after-input, sensitive path, MCP-concentrated trifecta) |

## Mutation Types (Adaptive Mode)

| Mutation | Technique | Expected Bypass Rate |
|----------|-----------|---------------------|
| homoglyph | Cyrillic/Latin lookalike substitution | Low (MEDIUM patterns detect) |
| encoding | URL-encode keywords | High (hooks normalize some, not all) |
| zero_width | Insert zero-width chars in keywords | Low (normalizer strips these) |
| case_alternation | aLtErNaTiNg case | Low (regex uses /i flag) |
| synonym | Replace with semantic equivalents | Medium (novel synonyms evade patterns) |

## Important

- This tests the plugin's OWN hooks — it does not perform real exploits
- No network calls, no file modifications, no LLM invocations
- Safe to run repeatedly — all state is cleaned up after each run
- Adaptive mode bypasses are **expected** — they document evasion resistance limits

## HTML Report

After producing the markdown red-team narrative report above:

1. Compute a temp markdown path:
   ```bash
   node -p "require('path').join(require('os').tmpdir(), 'sec-red-team-' + Date.now() + '.md')"
   ```
2. Use the Write tool to save the **entire markdown report you just produced** (per-category narrative + scenario pass/fail + defense score + adaptive-mode bypasses if `--adaptive`) to that temp path. Verbatim.
3. Run the renderer:
   ```bash
   node <plugin-root>/scripts/render-report.mjs red-team --in "<temp-md-path>"
   ```
   The CLI writes `reports/red-team-<YYYYMMDD-HHmmss>.html` relative to CWD and prints `file:///abs/path.html` on stdout.
4. Append to your response (markdown link, no bare URL):

   > **HTML-rapport:** [Åpne i nettleser](file:///abs/path.html)

If the CLI exits non-zero, mention the error but do not block — the markdown report above is the primary deliverable.