chore: Update security guidelines - #4468
Open
DrewBloechl wants to merge 1 commit into
Open
Conversation
Contributor
Summary by CodeRabbit
WalkthroughThe change adds security triage metadata and replaces generic security guidance with NICo-specific repository and REST API policies. ChangesSecurity governance
Estimated code review effort: 2 (Simple) | ~15 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
chet
added
the
rest-api
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
SECURITY.md (2)
252-259: 🔒 Security & Privacy | 🔵 Trivial | ⚡ Quick winMake supported security channels operator-verifiable.
This section tells operators to use maintained branches, tagged images, or designated commits. It does not identify the maintained branches or tags, support dates, or the method to verify that a commit is designated. Add a canonical support matrix or release-policy reference.
🤖 Prompt for 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. In `@SECURITY.md` around lines 252 - 259, Update the “Supported Versions and Security Updates” section in SECURITY.md to reference a canonical support matrix or release-policy document that identifies maintained branches, supported tags, support dates, and how operators can verify maintainer- or NVIDIA PSIRT-designated commits.
56-69: 🗄️ Data Integrity & Integration | 🔵 Trivial | ⚡ Quick winMake
.security-triage.yamlthe canonical source. The classification values matchSECURITY.md, but the basis text is duplicated and no validation prevents drift. Generate the classification section or add a CI consistency check.🤖 Prompt for 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. In `@SECURITY.md` around lines 56 - 69, Make .security-triage.yaml the canonical source for repository and service exposure classifications, then add CI validation that compares the corresponding SECURITY.md classification section against the canonical values and basis text. Update the documentation workflow or generation step to prevent manual drift, using the existing classification symbols and section as the synchronization target.
🤖 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 13-18: Update the vulnerability-reporting guidance in SECURITY.md
to match the repository’s actual configuration: enable GitHub private
vulnerability reporting before retaining the Security tab route, or remove that
route if it will remain disabled. Keep the NVIDIA disclosure and email options
unchanged.
---
Nitpick comments:
In `@SECURITY.md`:
- Around line 252-259: Update the “Supported Versions and Security Updates”
section in SECURITY.md to reference a canonical support matrix or release-policy
document that identifies maintained branches, supported tags, support dates, and
how operators can verify maintainer- or NVIDIA PSIRT-designated commits.
- Around line 56-69: Make .security-triage.yaml the canonical source for
repository and service exposure classifications, then add CI validation that
compares the corresponding SECURITY.md classification section against the
canonical values and basis text. Update the documentation workflow or generation
step to prevent manual drift, using the existing classification symbols and
section as the synchronization target.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 6934524e-11cf-415e-80a1-f5efb104a4c5
📒 Files selected for processing (3)
.security-triage.yamlSECURITY.mdrest-api/SECURITY.md
Comment on lines
+13
to
+18
| - Report via the [NVIDIA Vulnerability Disclosure Program](https://www.nvidia.com/en-us/security/) (preferred). | ||
| - E-Mail: [psirt@nvidia.com](mailto:psirt@nvidia.com) | ||
| - We encourage you to use the following PGP key for secure email communication: | ||
| [NVIDIA public PGP Key](https://www.nvidia.com/en-us/security/pgp-key) | ||
| - GitHub: Use the **Security** tab > **Report a vulnerability** to submit a | ||
| private report directly on this repository. |
Contributor
There was a problem hiding this comment.
🔒 Security & Privacy | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/sh
set -eu
for url in \
"https://www.nvidia.com/en-us/security/" \
"https://www.nvidia.com/en-us/security/pgp-key" \
"https://www.nvidia.com/en-us/security/psirt-policies/" \
"https://github.com/NVIDIA/infra-controller/security/advisories/new"
do
curl -fsSIL --location --max-time 15 "$url" >/dev/null
done
gh api repos/NVIDIA/infra-controller --jq '.security_and_analysis // {}'Repository: NVIDIA/infra-controller
Length of output: 164
🏁 Script executed:
set +e
for endpoint in \
"repos/NVIDIA/infra-controller/private-vulnerability-reporting" \
"repos/NVIDIA/infra-controller/security-and-analysis" \
"repos/NVIDIA/infra-controller"
do
echo "=== $endpoint ==="
gh api "$endpoint" --include 2>&1 | sed -n '1,80p'
echo "status=${PIPESTATUS[0]}"
doneRepository: NVIDIA/infra-controller
Length of output: 10713
Enable private vulnerability reporting before publishing.
NVIDIA/infra-controller reports {"enabled":false}, so the GitHub Security tab does not provide the private reporting route described here. Enable it or remove this route from SECURITY.md.
🤖 Prompt for 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.
In `@SECURITY.md` around lines 13 - 18, Update the vulnerability-reporting
guidance in SECURITY.md to match the repository’s actual configuration: enable
GitHub private vulnerability reporting before retaining the Security tab route,
or remove that route if it will remain disabled. Keep the NVIDIA disclosure and
email options unchanged.
Source: Path instructions
🔐 TruffleHog Secret Scan✅ No secrets or credentials found! Your code has been scanned for 700+ types of secrets and credentials. All clear! 🎉 🕐 Last updated: 2026-07-31 22:54:59 UTC | Commit: da70da4 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This updates the project security guidelines using the internal
generate-security-mdskill via Codex.Changes:
SECURITY.mdwith a more specific/verbose version generated by the skill.rest-api/SECURITY.mddoc to reference the one in the repo root..security-triage.yamldocument (with myself filled in as the confirmation for the classifications).Related issues
Type of Change
Breaking Changes
Testing