Metadata-Version: 2.4
Name: agentforge-guard-llmguard
Version: 0.2.4
Summary: LLM Guard scanners for AgentForge guardrails
Project-URL: Homepage, https://github.com/Scaffoldic/agentforge-py
Project-URL: Repository, https://github.com/Scaffoldic/agentforge-py
Project-URL: Documentation, https://github.com/Scaffoldic/agentforge-py
Project-URL: Changelog, https://github.com/Scaffoldic/agentforge-py/blob/main/CHANGELOG.md
Project-URL: Issues, https://github.com/Scaffoldic/agentforge-py/issues
Author: The AgentForge Authors
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agent,ai,guardrails,llm-guard,prompt-injection
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Security
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.13
Requires-Dist: agentforge-core~=0.2.4
Description-Content-Type: text/markdown

# agentforge-guard-llmguard

LLM Guard scanners for AgentForge guardrails (feat-018).

Wraps the [`llm-guard`](https://llm-guard.com) library. Adds the
`llmguard` validator to the `agentforge.yaml`
`modules.guardrails.input` section:

```yaml
modules:
  guardrails:
    input:
      - llmguard:
          scanners: ["prompt_injection", "ban_substrings", "secrets"]
          ban_substrings: ["password", "api_key"]
```

```bash
agentforge add module guard-llmguard
```

The shipped scanner subset covers `prompt_injection`, `jailbreak`,
`ban_substrings`, and `secrets`. The full upstream scanner catalogue
remains accessible by passing additional names through the
`scanners` list — LLM Guard resolves them server-side.
