Add mcp-security-baseline skill by Swethakumar1 · Pull Request #2212 · github/awesome-copilot

Swethakumar1 · 2026-07-04T00:04:57Z

Add skill: `mcp-security-baseline`

An Agent Skill that reviews MCP server and client source code against a security
baseline and produces a compliance report with file/line evidence.

Checks: 5 baseline controls (authentication & identity isolation, sessions, rate
limiting, input-schema validation, official-SDK usage), 7 RCE vectors (command injection,
dynamic code eval, unsafe deserialization, path traversal, SSTI, dependency hijacking,
SSRF), and the OWASP MCP Top 10. Six-step process; uses NEEDS INVESTIGATION when source
alone can't decide.

Distinct from the existing mcp-security-audit skill, which audits .mcp.json configuration — this reviews server/client source code.

Validation: npm run skill:validate ✅ and npm run build ✅ (adds one row to
docs/README.skills.md). Single self-contained SKILL.md (matches existing skills like
agent-owasp-compliance). Blind-tested against intentionally vulnerable MCP repos across
multiple models (100% recall on planted vulnerabilities, zero false negatives).

github-actions · 2026-07-04T00:05:25Z

🔒 PR Risk Scan Results

Scanned 2 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	2
ℹ️ Info	0

Severity	Rule	File	Line	Match
🟠	`package-exec-command`	`docs/README.skills.md`	31	\| [acreadiness-assess](../skills/acreadiness-assess/SKILL.md)<br />`gh skills install github/awesome-copilot acreadiness-assess` \| Run the AgentRC readiness assessment on the curre
🟠	`unpinned-version-indicator`	`skills/mcp-security-baseline/SKILL.md`	221	\| Dependency hijacking \| Unpinned deps such as `"lodash": "^4.0.0"`; internal package names resolvable from public registries \| Pin exact versions, keep lock files with integrity h

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

github-actions · 2026-07-04T00:07:00Z

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	npm warn EBADENGINE Unsupported engine {
ℹ️	npm warn EBADENGINE package: 'commander@15.0.0',
ℹ️	npm warn EBADENGINE required: { node: '>=22.12.0' },
ℹ️	npm warn EBADENGINE current: { node: 'v20.20.2', npm: '10.8.2' }
ℹ️	npm warn EBADENGINE }
ℹ️	npm warn deprecated prebuild-install@7.1.3: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
ℹ️	✅ mcp-security-baseline (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.

Full linter output

### Linting skills/mcp-security-baseline
npm warn EBADENGINE Unsupported engine {
npm warn EBADENGINE   package: 'commander@15.0.0',
npm warn EBADENGINE   required: { node: '>=22.12.0' },
npm warn EBADENGINE   current: { node: 'v20.20.2', npm: '10.8.2' }
npm warn EBADENGINE }
npm warn deprecated prebuild-install@7.1.3: No longer maintained. Please contact the author of the relevant native addon; alternatives are available.
✅ mcp-security-baseline (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed

Copilot

Pull request overview

Adds a new Agent Skill (mcp-security-baseline) to help reviewers assess MCP server/client source code against a defined security baseline and produce an evidence-backed compliance report, and updates the generated skills index to include it.

Changes:

Added mcp-security-baseline skill with a structured 6-step review process, baseline controls (MCP-01..05), RCE vector checks, and OWASP MCP Top 10 mapping.
Updated docs/README.skills.md to include the new skill entry.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
skills/mcp-security-baseline/SKILL.md	New skill definition and detailed review checklist/reporting format for MCP implementation security reviews.
docs/README.skills.md	Adds the new skill to the skills documentation index.

An Agent Skill that reviews MCP server and client source code against a security baseline (5 controls, 7 RCE vectors, OWASP MCP Top 10) and produces a compliance report with file/line evidence. Complements mcp-security-audit, which checks .mcp.json configuration. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

aaronpowell

Very minor nitpicks on the skill

- Remove the top-level `keywords` field: it is not a recognized skill front-matter field and is ignored (skills are indexed for search by name + description only). The keyword terms are already present in the description, so discovery is unaffected. - Link the MCP 2025-03-26 specification at the protocol-version check so the agent has it for quick reference. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

…rent MCP spec - Change the unsafe-deserialization example from `yaml.load(..., Loader=yaml.FullLoader)` to `Loader=yaml.UnsafeLoader` to reflect genuinely unsafe usage. - Add a link to the current MCP spec revision (2025-11-25) alongside the 2025-03-26 baseline on the protocol-version check. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

+| Pattern | Transport |
+|---|---|
+| `transport="http"` or `transport="sse"` | HTTP/SSE |
+| `StreamableHttpServerTransport` | HTTP (TS/JS) |
+| `SSEServerTransport` | SSE (TS/JS) |
+| `WithHttpTransport()` | HTTP (C#) |
+| `host="0.0.0.0"` | All-interfaces binding |
+| Express `.listen(port)` with MCP routes | HTTP (default `0.0.0.0`) |
+| `EXPOSE` in Dockerfile + MCP server | Network-exposed |


+### Step 3 — Check baseline controls
+- For **network-exposed servers**, check **MCP-01** through **MCP-05**.
+- For **local/STDIO servers**, do not mark baseline controls PASS/FAIL; give best-practice notes and continue to RCE review.
+- For **clients**, only review token/session handling explicitly visible in client code; do not apply the server baseline unless the user asks for client-side risk review.
+
+**Completion criterion:** Each applicable control has a supported status.


Copilot

Review details

Files reviewed: 2/2 changed files
Comments generated: 2
Review effort level: Low

+### Step 3 — Check baseline controls
+- For **network-exposed servers**, check **MCP-01** through **MCP-05**.
+- For **local/STDIO servers**, do not mark baseline controls PASS/FAIL; give best-practice notes and continue to RCE review.
+- For **clients**, only review token/session handling explicitly visible in client code; do not apply the server baseline unless the user asks for client-side risk review.
+
+**Completion criterion:** Each applicable control has a supported status.


+## Process
+
+### Step 1 — Classify the target
+- Check **MCP protocol version [2025-03-26](https://modelcontextprotocol.io/specification/2025-03-26) or later** (current: [2025-11-25](https://modelcontextprotocol.io/specification/2025-11-25)). Flag older versions as a finding but continue the review.


github-actions · 2026-07-09T00:56:15Z

🔍 Potential Duplicate Resources Detected

This PR adds a resource that may be similar to an existing one in the repository. Please review this potential overlap before merging to avoid redundancy.

Note: This PR was already merged — this check is advisory and informational only.

Possible Duplicates

Group 1: MCP security review skills

Resource	Type	Description
`skills/mcp-security-baseline/` (this PR)	Skill	Review MCP server and client source code against a security baseline — authentication, sessions, rate limiting, input-schema validation, RCE vectors, and the OWASP MCP Top 10
`skills/mcp-security-audit/` (existing)	Skill	Audit MCP server configurations (`.mcp.json` files) for security issues — hardcoded secrets, shell injection in args, unpinned dependencies, unapproved servers

Why flagged: Both skills share the mcp-security- name prefix and both focus on MCP security. A user looking for "MCP security" might not immediately know which skill applies to their use case.

Suggestion: The two skills cover genuinely different layers — configuration auditing vs. source code review — and the PR description explicitly acknowledges this distinction. Consider whether the skill's description and use-case examples make the difference from mcp-security-audit clear enough at a glance (e.g., triggering on "review my MCP server code" vs. "check my .mcp.json").

💡 This is an advisory check only. If these are intentionally different, no action is needed — feel free to proceed with your PR.

Generated by PR Duplicate Check for #2212 · 52 AIC · ⌖ 6.22 AIC · ⊞ 5.9K · ◷

Copilot AI review requested due to automatic review settings July 4, 2026 00:04

Swethakumar1 requested a review from aaronpowell as a code owner July 4, 2026 00:04

github-actions Bot added new-submission PR adds at least one new contribution skills PR touches skills labels Jul 4, 2026

Copilot started reviewing on behalf of Swethakumar1 July 4, 2026 00:05 View session

Copilot AI reviewed Jul 4, 2026

View reviewed changes

Swethakumar1 force-pushed the add-mcp-security-baseline-skill branch from 948e63d to e7ab12c Compare July 4, 2026 00:20

aaronpowell reviewed Jul 7, 2026

View reviewed changes

Comment thread skills/mcp-security-baseline/SKILL.md Outdated

Comment thread skills/mcp-security-baseline/SKILL.md Outdated

Copilot AI review requested due to automatic review settings July 8, 2026 19:46

Copilot stopped reviewing on behalf of Swethakumar1 due to an error July 8, 2026 19:46
An unexpected error occurred. For more details, see the detailed logs in GitHub Actions.

Copilot AI reviewed Jul 8, 2026

View reviewed changes

Comment thread skills/mcp-security-baseline/SKILL.md Outdated

Comment thread skills/mcp-security-baseline/SKILL.md

Copilot AI review requested due to automatic review settings July 8, 2026 20:06

Copilot stopped reviewing on behalf of Swethakumar1 due to an error July 8, 2026 20:06
An unexpected error occurred. For more details, see the detailed logs in GitHub Actions.

Copilot AI reviewed Jul 8, 2026

View reviewed changes

aaronpowell approved these changes Jul 9, 2026

View reviewed changes

Merge branch 'main' into add-mcp-security-baseline-skill

68a6fc2

Copilot AI review requested due to automatic review settings July 9, 2026 00:48

aaronpowell enabled auto-merge (squash) July 9, 2026 00:49

Copilot started reviewing on behalf of aaronpowell July 9, 2026 00:49 View session

aaronpowell merged commit 72fae20 into github:main Jul 9, 2026
9 checks passed

Copilot AI reviewed Jul 9, 2026

View reviewed changes

Swethakumar1 mentioned this pull request Jul 9, 2026

Rename mcp-security-baseline skill to mcp-implementation-security-review #2257

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add mcp-security-baseline skill#2212

Add mcp-security-baseline skill#2212
aaronpowell merged 4 commits into
github:mainfrom
Swethakumar1:add-mcp-security-baseline-skill

Swethakumar1 commented Jul 4, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jul 4, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jul 4, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

aaronpowell left a comment

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

github-actions Bot commented Jul 9, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

Swethakumar1 commented Jul 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Add skill: mcp-security-baseline

Uh oh!

github-actions Bot commented Jul 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔒 PR Risk Scan Results

Uh oh!

github-actions Bot commented Jul 4, 2026

🔍 Vally Lint Results

Summary

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

aaronpowell left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Review details

Uh oh!

github-actions Bot commented Jul 9, 2026

🔍 Potential Duplicate Resources Detected

Possible Duplicates

Group 1: MCP security review skills

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Swethakumar1 commented Jul 4, 2026 •

edited

Loading

Add skill: `mcp-security-baseline`

github-actions Bot commented Jul 4, 2026 •

edited

Loading