Update README.md

[KanishkThamman]

Contribution Type

• Resource, standard, framework, or research
• Tool or benchmark
• Case study
• Secure engineering pattern or architecture
• Governance, contribution, or repository maintenance
• Other

Evidence And Scope

• Source or evidence: NuGuard official documentation and repository materials, plus any primary technical references linked in this PR.
• Producer or publisher: NuGuard maintainers.
• Risks, behaviours, controls, or evaluation methods covered: Runtime guardrails, policy enforcement, agent action constraints, and security evaluation considerations for agentic workflows.
• Maturity or evidence level: Emerging practical adoption; claims should be treated as implementation-dependent.
• Last-checked date, if external: 1 August 2026.

Review Focus

Please review for:

1. Neutral, evidence-led language (no overstatement of maturity or effectiveness).
2. Clear separation between documented features and independently validated outcomes.
3. Consistency with repository scope on agentic execution security and British English usage.
4. Alignment between cited evidence and any rubric/scoresheet scoring.

Checklist

• The change is relevant to agentic execution security.
• Claims are evidence-led and do not overstate repository maturity.
• British English is used except for established names such as AI Defense Plane.
• No unnecessary operational exploit detail is included.
• No copied source material is included when a summary and link would be enough.
• No generated outputs, built documentation, logs, traces, screenshots, reports, exports, or local artefacts are included.
• If this PR adds a new resource, case study, or benchmark, a corr

Note

Add NuGuard entry to README under 'Tool Use, MCP, and Runtime Security'

Adds a bullet for NuGuard in README.md with a link and description covering AI-SBOM generation, red-teaming of tool use/MCP integrations/APIs, and automated remediation. Also removes a stray - line after the section header.

^{Macroscope summarized 7e85647.}

Summary by CodeRabbit

• Documentation
  • Added NuGuard to the security catalogue.
  • Documented AI-SBOM generation, red-teaming coverage, and automated remediation output.

[coderabbitai]

📝 Walkthrough

Walkthrough

Changes

NuGuard catalogue

Layer / File(s)	Summary
Add NuGuard resource README.md	Adds NuGuard to the Tool Use, MCP, and Runtime Security catalogue with details about AI-SBOM generation, red-teaming, security testing, and automated remediation output.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Suggested reviewers: natnew

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description covers most required sections, but the required Summary section is missing and the final checklist item is truncated.	Add a Summary section and complete the final checklist item, including the required rubrics/scoresheet status.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Title check	✅ Passed	The title identifies the README change but does not state the primary change, which is the addition of NuGuard.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}

[coderabbitai]

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 `@README.md`:
- Around line 177-180: Update the NuGuard entry in the README to qualify that
red-team testing applies when a target is running and that remediation output is
best-effort, avoiding wording that implies every scan performs red-teaming or
guarantees fixes.

🪄 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: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 0865593a-37d7-4af9-a7eb-5c0fffe4c35a

📥 Commits

Reviewing files that changed from the base of the PR and between ea0dd4a and 7e85647.

📒 Files selected for processing (1)

• README.md

[coderabbitai]

🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win

Qualify the runtime and remediation claims.

The entry presents red-teaming and remediation as unconditional capabilities. NuGuard documentation states that red-team tests require a running target and that remediation is best-effort. Use wording that does not imply that every scan performs these steps or that NuGuard applies guaranteed fixes. (github.com)

Suggested wording

-- Open-source toolkit that builds an AI-SBOM from agent codebases, then red-teams tool use, MCP integrations, and API surfaces for prompt injection and data exfiltration, with automated remediation output.
+- Open-source toolkit that can build an AI-SBOM from agent codebases and, when configured with a live target, red-team tool use, MCP integrations, and API surfaces for prompt injection and data exfiltration, with best-effort remediation suggestions.

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	- [NuGuard](https://github.com/NuGuardAI/nuguard) - Open-source toolkit that
	builds an AI-SBOM from agent codebases, then red-teams tool use, MCP
	integrations, and API surfaces for prompt injection and data exfiltration,
	with automated remediation output.
	- [NuGuard](https://github.com/NuGuardAI/nuguard) - Open-source toolkit that
	can build an AI-SBOM from agent codebases and, when configured with a live
	target, red-team tool use, MCP integrations, and API surfaces for prompt
	injection and data exfiltration, with best-effort remediation suggestions.

🤖 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 `@README.md` around lines 177 - 180, Update the NuGuard entry in the README to
qualify that red-team testing applies when a target is running and that
remediation output is best-effort, avoiding wording that implies every scan
performs red-teaming or guarantees fixes.