> ## Documentation Index
> Fetch the complete documentation index at: https://ctpf.q-uestionable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Inject CLI Reference

> Commands for tool poisoning and injection campaigns

Use the `qai inject` subcommand to serve adversarial payloads, run campaigns against LLM models, and analyze results.

```bash theme={null}
qai inject --help
```

## qai inject serve

Start a malicious MCP server that serves poisoned tool definitions. Useful for testing agent resilience or simulating compromised MCP servers in controlled environments.

```bash theme={null}
qai inject serve --transport <type> [OPTIONS]
```

### Options

| Flag            | Type   | Required | Description                                        |
| --------------- | ------ | -------- | -------------------------------------------------- |
| `--transport`   | enum   | Yes      | Transport type: `stdio` or `streamable-http`       |
| `--port`        | int    | No       | Port for streamable-http (default: `8888`)         |
| `--payload-dir` | string | No       | Directory containing custom payload YAML templates |
| `--config`      | string | No       | YAML file with list of payload names to serve      |

### Examples

Serve all default payloads via stdio:

```bash theme={null}
qai inject serve --transport stdio
```

Serve via HTTP on a custom port:

```bash theme={null}
qai inject serve \
  --transport streamable-http \
  --port 9000
```

Serve only specific payloads listed in a config file:

```bash theme={null}
qai inject serve \
  --transport stdio \
  --config my-payloads.yaml
```

<Tip>
  Use `qai inject list-payloads` to see available payloads before running a campaign.
</Tip>

## qai inject campaign

Run an automated injection campaign against an LLM model. Tests each payload by serving it as a poisoned tool and measuring the model's susceptibility.

```bash theme={null}
qai inject campaign [OPTIONS]
```

### Options

| Flag          | Type   | Required | Description                                                                                                                                                                |
| ------------- | ------ | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `--model`     | string | Yes\*    | Model ID in provider/model format (e.g., `anthropic/claude-sonnet-4-20250514`, `openai/gpt-4o`). Falls back to `QAI_MODEL` env var. Bare model names default to Anthropic. |
| `--rounds`    | int    | No       | Number of attempts per payload (default: `1`)                                                                                                                              |
| `--output`    | string | No       | Output directory for campaign JSON (default: `.`)                                                                                                                          |
| `--payloads`  | string | No       | Comma-separated payload names, or `all` (default: `all`)                                                                                                                   |
| `--technique` | enum   | No       | Filter by technique: `description_poisoning`, `output_injection`, `cross_tool_escalation`                                                                                  |
| `--target`    | string | No       | Filter by target agent type (e.g., `claude`, `gpt`)                                                                                                                        |

### Setting Credentials

Store API keys in the OS keyring (prompts for key with masked input):

```bash theme={null}
qai config set-credential anthropic
qai config set-credential openai
```

Alternatively, set provider environment variables directly (e.g., `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`). See [Provider Configuration](/config/providers) for details.

### Examples

Run campaign against Claude Sonnet:

```bash theme={null}
qai inject campaign \
  --model anthropic/claude-sonnet-4-20250514 \
  --rounds 1 \
  --output results/
```

Run campaign against OpenAI GPT-4o with specific technique:

```bash theme={null}
qai inject campaign \
  --model openai/gpt-4o \
  --technique description_poisoning \
  --rounds 2 \
  --output results/
```

Run campaign on specific payloads only:

```bash theme={null}
qai inject campaign \
  --model anthropic/claude-sonnet-4-20250514 \
  --payloads exfil_via_important_tag,preference_manipulation
```

<Note>
  Campaign results are automatically saved to the database. Results are also written as JSON to the `--output` directory.
</Note>

## qai inject list-payloads

List available injection payload templates and their metadata.

```bash theme={null}
qai inject list-payloads [OPTIONS]
```

### Options

| Flag          | Type   | Description                                                                               |
| ------------- | ------ | ----------------------------------------------------------------------------------------- |
| `--technique` | enum   | Filter by technique: `description_poisoning`, `output_injection`, `cross_tool_escalation` |
| `--target`    | string | Filter by target agent type (e.g., `claude`, `gpt`)                                       |

### Examples

List all payloads:

```bash theme={null}
qai inject list-payloads
```

List description poisoning payloads only:

```bash theme={null}
qai inject list-payloads --technique description_poisoning
```

List payloads designed for Claude:

```bash theme={null}
qai inject list-payloads --target claude
```

## qai inject report

Generate a summary report from saved campaign JSON results.

```bash theme={null}
qai inject report --input <path> [OPTIONS]
```

### Options

| Flag              | Type   | Required | Description                                             |
| ----------------- | ------ | -------- | ------------------------------------------------------- |
| `--input` / `-i`  | string | Yes      | Path to campaign JSON file (from `qai inject campaign`) |
| `--format` / `-f` | enum   | No       | Output format: `table` or `json` (default: `table`)     |

### Examples

Display table summary:

```bash theme={null}
qai inject report -i results/campaign-20260322-120000-000000.json
```

Output raw JSON:

```bash theme={null}
qai inject report -i results/campaign-20260322-120000-000000.json -f json
```

The table shows each payload, technique used, outcome classification, and evidence snippet from the LLM response.