Skip to content
Back to skills

Agt Security

ASecurity

Provides sandboxing validation, HMAC key rotation, and budget verification to manage security boundaries under Agentic Group Theory (AGT).

  • 7 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agentspythonbashsecurity

Works with

  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 3, 2026

npx -y skills add richfrem/agent-plugins-skills --skill agt-security --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agt Security?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agt Security
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-agt-security/badge)](https://www.skillsdirectory.com/skills/richfrem-agt-security)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agt-security
plugin: cli-agents
description: >-
  Provides sandboxing validation, HMAC key rotation, and budget verification to 
  manage security boundaries under Agentic Group Theory (AGT).
allowed-tools: Bash, Read, Write
---

# Agentic Group Theory Security (agt-security)

Manages local execution sandboxes, verifies process hygiene limits, and rotates cryptographic HMAC bus keys under Agentic Group Theory (AGT).

## Contents
- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Workflow](#workflow)
- [Verification](#verification)
- [References](#references)

## Critical Constraints
- **Environment Hygiene**: Ensure banned execution variables (`PYTHONPATH`, `PYTHONHOME`, `LD_PRELOAD`, `DYLD_LIBRARY_PATH`) are scrubbed before subprocess launch.
- **Path Containment**: Ensure filesystem operations outside declared root boundaries raise explicit `PermissionError` exceptions.
- **Key Permission Enforcement**: HMAC session keys must be created exclusively with `0600` permissions inside protected secret storage (`context/exploration/.secrets/`).
- **Zero Key Leakage**: Never print, log, or leak raw HMAC key bytes to stdout, telemetry, or conversational outputs.

## Quick start

```bash
# Verify sandbox hygiene and path containment
python3 plugins/cli-agents/scripts/agt_ops.py verify-sandbox

# Rotate local HMAC session signing key
python3 plugins/cli-agents/scripts/agt_ops.py rotate-key
```

## Workflow

1. **Phase 1: Environment Hygiene Check**: Run `agt_ops.py verify-sandbox` to verify environment variable sanitization in subprocess runners.
2. **Phase 2: Boundary Containment Verification**: Confirm that path containment rules trigger `PermissionError` when accessing out-of-bounds directories.
3. **Phase 3: Cryptographic Key Rotation**: Execute `agt_ops.py rotate-key` to generate a 32-byte cryptographically secure HMAC session key with `0600` mode.
4. **Phase 4: Permission Verification**: Verify file mode permissions on `session_hmac.key` to ensure unauthorized read access is prevented.

## Verification

```bash
# Run sandbox verification
python3 plugins/cli-agents/scripts/agt_ops.py verify-sandbox

# Audit skill compliance
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/cli-agents/skills/agt-security --mode source
```

## References
- [acceptance-criteria.md](references/acceptance-criteria.md) - AGT operational security criteria.

Files in this skill

  • SKILL.md1.3 KB
  • evals/evals.json601 B
  • evals/results.tsv34 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.