agentic_security vs cc-safety-net
The two are close in size: 2.0k stars for agentic_security, 1.5k for cc-safety-net. Over the days we have tracked them agentic_security moved +4.7% and cc-safety-net +2.9%, so agentic_security is growing faster right now.
They split the axes: agentic_security leads on model freedom, cc-safety-net on context depth.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Agentic Security focuses on agent/workflow-focused, multimodal (text, image, audio) and multi-step attack/fuzzing capabilities (including RL-based and dataset mutation approaches) to evaluate LLM vulnerabilities beyond single-shot prompt tests.
- Stars
- 2.0k
- Tracked growth
- +4.7%
- Maturity
- ●●●●●
- Last commit
- 3d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Your LLM API key, usage billed by the provider
Parses command semantics (including shell wrappers and interpreter one-liners) to block destructive commands and secret access before they execute across many coding agent CLIs.
- Stars
- 1.5k
- Tracked growth
- +2.9%
- Maturity
- ●●●●●
- Last commit
- 56m ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Free, local install (requires Node.js)
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | agentic_security | cc-safety-net |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Prompt-only | ●●●●● Command + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Thresholds/config | ●●●●● Presets + audit |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config + modules | ●●●●● Rulebooks & per-project |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Local-only |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own-key | ●●●●● Multiple agent CLIs |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command start | ●●●●● One-command install |
Which one to pick
Pick agentic_security if…
Easy setup — pip-installable and runnable locally with configurable datasets and modules to quickly run multimodal, multi-step vulnerability scans against your LLM endpoints.
- Model freedom: Bring-your-own-key (5/5 against 3/5)
Pick cc-safety-net if…
Safety-first — Blocks destructive git/filesystem commands and secret access before AI agents run them, using semantic command analysis, configurable rulebooks, presets, and a local audit trail.
- Context depth: Command + related files (3/5 against 1/5)
What people want from each one
msoedov/agentic_security
Hacker News: Agentic Security – LLM Vulnerability Scanner drew 2 points and 0 comments.
Questions people ask
Is agentic_security better than cc-safety-net?
They split the axes: agentic_security leads on model freedom, cc-safety-net on context depth. agentic_security is worth picking when easy setup — pip-installable and runnable locally with configurable datasets and modules to quickly run multimodal, multi-step vulnerability scans against your LLM endpoints.
Which of agentic_security and cc-safety-net keeps my code private?
agentic_security: Self-hostable (4/5). cc-safety-net: Local-only (5/5).
What does each one cost to run?
agentic_security: Your LLM API key, usage billed by the provider. cc-safety-net: Free, local install (requires Node.js).
Full profiles: msoedov/agentic_security and kenryu42/cc-safety-net. Everything else in Security & guardrails.