Skip to content

Conversation

@kenryu42
Copy link

@kenryu42 kenryu42 commented Jan 7, 2026

Hello, this PR adds a new plugin to the https://opencode.ai/docs/ecosystem/ page.

cc-safety-net

This plugin acts as a safety net for AI coding agents, catching destructive git and filesystem commands before they execute. It provides semantic command analysis that goes beyond simple prefix matching—parsing arguments, understanding flag combinations, recursively analyzing shell wrappers, and distinguishing safe operations from dangerous ones.

Key features:

  • Blocks destructive git commands (git reset --hard, git push --force, git checkout --, etc.)
  • Prevents dangerous filesystem operations (rm -rf outside cwd, root/home deletion)
  • Detects shell wrappers (bash -c, sh -c) and interpreter one-liners (python -c)
  • Supports custom blocking rules via .safety-net.json
  • Includes audit logging and secret redaction

npm: cc-safety-net
Read more about it here.

Thanks.

@github-actions
Copy link
Contributor

github-actions bot commented Jan 7, 2026

The following comment was made by an LLM, it may be inaccurate:

No duplicate PRs found

The search results show only the current PR (#7212) and other ecosystem plugin documentation PRs that are unrelated (Fast Apply, opencode-synced, opencode-browser, and Opencode-Openmemory). There are no existing duplicate PRs for the cc-safety-net plugin addition.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant