chore(security): add SECURITY.md for coordinated vulnerability disclosure#6284
chore(security): add SECURITY.md for coordinated vulnerability disclosure#6284camgrimsec wants to merge 2 commits into
Conversation
There was a problem hiding this comment.
Summary: This PR adds a SECURITY.md disclosure policy and does not modify runtime code, authentication, authorization, data handling, or exposed endpoints. No exploitable security vulnerabilities were identified.
Risk: Low risk. The change is documentation-only and does not introduce new attack surfaces or alter security boundaries.
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
📝 WalkthroughWalkthroughA new ChangesSecurity Policy
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@SECURITY.md`:
- Around line 14-16: The current SECURITY.md file directs users to README-listed
channels as a fallback if GitHub's private reporting is unavailable, but these
channels are not guaranteed to be private, which weakens the security disclosure
promise. Replace the reference to README-listed channels with a dedicated
private contact method (such as a specific email address, contact form, or other
guaranteed private channel). This ensures that anyone reporting a vulnerability
has a reliable private communication path even if GitHub advisories are
inaccessible.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
…sure
CrewAI currently has no SECURITY.md, which means GitHub does not show
the 'Report a vulnerability' shortcut on the repo's Security tab and
researchers have no documented private channel. For a 28k-star project
that ships into production agent stacks, having a documented disclosure
path is table stakes.
This adds a minimal, opinionated SECURITY.md that:
- Points reporters at GitHub's private vulnerability reporting
- Lists what makes a good report (component, version, repro, impact)
- Describes a standard coordinated-disclosure flow via GHSA
- Clarifies what is out of scope (user prompts, upstream LLM provider
outages, third-party tools)
Intentionally avoids hard response-time SLAs so maintainers can adjust
to capacity. No code paths, no public API, single new file.
CodeRabbit flagged that the README-listed channels (Discord, X, general support) are not guaranteed to be private and should not be used as a disclosure fallback. Replaced with explicit guidance plus a TODO for maintainers to fill in a dedicated security alias before merge.
7197947 to
e4e8920
Compare
|
Quick update:
@joaomdmoura @lucasgomide — ready for human review when one of you has a minute. Happy to adjust the disclosure email / contact pattern if you'd prefer something different from the placeholder. |
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed: #!/bin/bash
cat SECURITY.mdLength of output: 2355
The only outstanding item before merge is for a maintainer to swap the placeholder comment with a real |
CrewAI currently has no SECURITY.md, which means GitHub does not show the 'Report a vulnerability' shortcut on the repo's Security tab and researchers have no documented private channel. For a 28k-star project that ships into production agent stacks, having a documented disclosure path is table stakes.
This adds a minimal, opinionated SECURITY.md that:
Intentionally avoids hard response-time SLAs so maintainers can adjust to capacity. No code paths, no public API, single new file.
Summary by CodeRabbit