---
id: code-safety
track: coding
version: 0.0.5
label: advisory
keyword: advise
where: text
sha256: 05eb5231e4f5eaaefcbb907e0a727e9fc0319a520fcb8541e9bfddcf9b44edd4
source: https://github.com/open-coder-ai/chock-catalog/tree/1e60d211c1bb767152c6ab0167932da06ab3a10f/base/code-safety
catalog_ref: 1e60d211c1bb767152c6ab0167932da06ab3a10f
---

# Code Safety

code-safety · version 0.0.5

Advisory — Advisory only. It is skill text, and nothing stops a violation. Chock adds friction. It is not a security boundary. 

In a git repo: advisory (The agent reads the text, and nothing stops a violation.)



## What it does

Trigger: secrets, eval/exec, unsanitized SQL, hallucinated dependencies. avoid: committing credentials, adding unverified packages, executing dynamic code. Install scan-secrets (commit, agent write) for secrets and verify-dependency-exists (opt-in; needs an allowlist) for dependencies. Advisory: eval/exec and SQL guidance; a gate decides only the non-literal slice (agentic-code-security code pack: Python eval/exec, SQL built from strings in Python and JS).

## Its label on each agent

- Claude Code (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=claude-code&p=code-safety
- Cursor (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=cursor&p=code-safety
- Codex (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=codex&p=code-safety
- GitHub Copilot (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=copilot&p=code-safety
- Devin (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=devin&p=code-safety
- Grok (tested): Not graded yet for Grok. Builder: /coding/builder/#client=grok&p=code-safety
- goose (tested): Not graded yet for goose. Builder: /coding/builder/#client=goose&p=code-safety
- Antigravity (tested): Not graded yet for Antigravity. Builder: /coding/builder/#client=antigravity&p=code-safety
- OpenHands (untested): Not graded yet for OpenHands. Builder: /coding/builder/#client=openhands&p=code-safety
- Kimi Code (untested): Not graded yet for Kimi Code. Builder: /coding/builder/#client=kimi-code&p=code-safety
- Factory Droid (untested): Not graded yet for Factory Droid. Builder: /coding/builder/#client=factory-droid&p=code-safety

## What it misses

This policy does not state what it misses.

## Latest change

0.0.5 · 2026-10-27 — Title wording only (IR-F40): "Code Safety Rule" is now "Code Safety". The id, guard and tests are unchanged.

## Provenance

- Tested by 0 of 4 cases run automatically
- SHA-256: `05eb5231e4f5eaaefcbb907e0a727e9fc0319a520fcb8541e9bfddcf9b44edd4`
- Catalog commit: https://github.com/open-coder-ai/chock-catalog/commit/1e60d211c1bb767152c6ab0167932da06ab3a10f
- Source: https://github.com/open-coder-ai/chock-catalog/tree/1e60d211c1bb767152c6ab0167932da06ab3a10f/base/code-safety (catalog path `base/code-safety`)
- Presets: Safety guidance
- JSON: `/api/coding/policies/code-safety.json`
- Report a problem: https://chock.sh/report/?policy=code-safety&version=0.0.5&page=%2Fcoding%2Fpolicies%2Fcode-safety%2F