Skip to content

Commit bcc9638

Browse files
AgriciDanielclaude
AgriciDaniel
and
claude
committed
Security remediation + Anthropic marketplace compliance
15-fix security remediation from self-audit (SECURITY-AUDIT-2026-04-15.md): - Remove WebFetch/WebSearch from allowed-tools (VULN-003/006) - Add prompt injection defense to agent dispatch (VULN-001) - Add per-agent tool restrictions for all 8 agents (VULN-010) - Add .claude/ to file exclusion list (VULN-004) - Add evidence redaction rules for secret masking (VULN-007) - Add Step 2.5 agent result validation (VULN-013) - Add integrity verification to install.sh (VULN-002) - Fix permission path mismatch in settings (VULN-014) - Remove nonexistent install.ps1 references (VULN-015) - Correct OWASP 2025 references to 2021 (VULN-011/012) - Remove unsubstantiated statistical claims (VULN-016/017) - Harden .gitignore with cert/key patterns (VULN-019) Marketplace compliance: - Fix plugin.json author format (string → object) - Add keywords and repository fields to plugin.json - Add plugin installation method to README - Align badges with actual capabilities (14 languages) New files: CHANGELOG.md, checksums.sha256, CI/CD pipeline, issue templates Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1 parent 2987974 commit bcc9638

13 files changed

Lines changed: 1243 additions & 37 deletions

File tree

‎.claude-plugin/plugin.json‎

Lines changed: 18 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,23 @@
11
{
22
"name": "cybersecurity",
33
"version": "1.0.0",
4-
"description": "AI-powered cybersecurity code review with 8 specialist agents, OWASP 2025, CWE Top 25, MITRE ATT&CK, and framework-aware false-positive suppression",
5-
"author": "AgriciDaniel",
4+
"description": "AI-powered cybersecurity code review with 8 specialist agents, OWASP Top 10:2021, CWE Top 25:2024, MITRE ATT&CK v15, and framework-aware false-positive suppression",
5+
"author": {
6+
"name": "AgriciDaniel"
7+
},
68
"license": "MIT",
7-
"homepage": "https://github.com/AgriciDaniel/claude-cybersecurity"
9+
"homepage": "https://github.com/AgriciDaniel/claude-cybersecurity",
10+
"repository": "https://github.com/AgriciDaniel/claude-cybersecurity",
11+
"keywords": [
12+
"security",
13+
"cybersecurity",
14+
"code-review",
15+
"owasp",
16+
"cwe",
17+
"vulnerability-scanner",
18+
"secret-detection",
19+
"sast",
20+
"appsec",
21+
"threat-modeling"
22+
]
823
}

‎.github/ISSUE_TEMPLATE/config.yml‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
blank_issues_enabled: false
2+
contact_links:
3+
- name: Security Vulnerability
4+
url: https://github.com/AgriciDaniel/claude-cybersecurity/security/advisories/new
5+
about: Report security vulnerabilities privately
6+
- name: Bug Report
7+
url: https://github.com/AgriciDaniel/claude-cybersecurity/issues/new
8+
about: Report detection accuracy issues or bugs

‎.github/workflows/ci.yml‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
name: CI
2+
3+
on:
4+
push:
5+
branches: [main]
6+
pull_request:
7+
branches: [main]
8+
9+
jobs:
10+
validate:
11+
runs-on: ubuntu-latest
12+
steps:
13+
- uses: actions/checkout@v4
14+
15+
- name: Shellcheck
16+
run: shellcheck install.sh uninstall.sh
17+
18+
- name: Validate Markdown
19+
uses: DavidAnson/markdownlint-cli2-action@v19
20+
with:
21+
globs: 'skills/**/*.md'
22+
23+
- name: Verify checksums
24+
run: |
25+
if [ -f checksums.sha256 ]; then
26+
sha256sum -c checksums.sha256
27+
fi
28+
29+
- name: Cross-reference check
30+
run: |
31+
grep -oP 'references/[a-z-/]+\.md' skills/cybersecurity/SKILL.md | sort -u | while read ref; do
32+
if [ ! -f "skills/cybersecurity/$ref" ]; then
33+
echo "ERROR: $ref referenced in SKILL.md but does not exist"
34+
exit 1
35+
fi
36+
done

‎.gitignore‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,14 @@ desktop.ini
1515
.env.*
1616
!.env.example
1717

18+
# Certificates and private keys
19+
*.pem
20+
*.key
21+
*.p12
22+
*.pfx
23+
*.jks
24+
*.crt
25+
1826
# Python
1927
__pycache__/
2028
*.pyc

‎CHANGELOG.md‎

Lines changed: 34 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
# Changelog
2+
3+
All notable changes to claude-cybersecurity will be documented in this file.
4+
5+
## [Unreleased]
6+
### Security
7+
- Remove WebFetch/WebSearch phantom permissions (VULN-003, VULN-006)
8+
- Add prompt injection defense to agent dispatch (VULN-001)
9+
- Add .claude/ to file exclusion list (VULN-004)
10+
- Add integrity verification to install script (VULN-002)
11+
- Fix permission path mismatch in settings.local.json (VULN-014)
12+
- Add per-agent tool restrictions (VULN-010)
13+
- Add evidence redaction rules for secret masking (VULN-007)
14+
- Add agent failure handling with Step 2.5 validation (VULN-013)
15+
16+
### Fixed
17+
- Correct OWASP Top 10 references from 2025 to 2021
18+
- Remove unsubstantiated statistical claims
19+
- Remove references to nonexistent install.ps1
20+
- Harden .gitignore with certificate/key patterns
21+
22+
### Added
23+
- CI/CD pipeline with shellcheck, markdown linting, and checksum verification
24+
- checksums.sha256 for file integrity verification
25+
- CHANGELOG.md for release tracking
26+
27+
## [1.0.0] - 2026-04-11
28+
### Added
29+
- Initial release
30+
- 8 parallel specialist agents with weighted scoring
31+
- 25 CWE categories, 11 language pattern files, 4 IaC pattern files
32+
- STRIDE threat modeling, MITRE ATT&CK v15 mapping
33+
- Framework-aware false-positive suppression (10 frameworks)
34+
- Compliance matrix (PCI DSS 4.0, HIPAA, SOC 2, GDPR, NIST 800-53)

‎README.md‎

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -7,38 +7,38 @@
77
<img src="https://img.shields.io/badge/claude--code-skill-blueviolet" alt="Claude Code Skill">
88
<img src="https://img.shields.io/badge/agents-8-00ff88" alt="8 Specialist Agents">
99
<img src="https://img.shields.io/badge/CWE%20Top%2025-100%25-red" alt="CWE Top 25 Coverage">
10-
<img src="https://img.shields.io/badge/OWASP-2025-orange" alt="OWASP 2025">
11-
<img src="https://img.shields.io/badge/languages-11-blue" alt="11 Languages">
10+
<img src="https://img.shields.io/badge/OWASP-2021-orange" alt="OWASP 2021">
11+
<img src="https://img.shields.io/badge/languages-14-blue" alt="14 Languages">
1212
</p>
1313

1414
---
1515

1616
**The most comprehensive AI-powered cybersecurity code review skill for Claude Code.** Spawns 8 parallel specialist agents to audit your codebase across vulnerability detection, authorization verification, secret scanning, supply chain analysis, IaC security, threat intelligence (malware/C2/backdoor detection), AI-generated code patterns, and business logic flaws.
1717

18-
**Surpasses GitHub Advanced Security** by detecting what static tools architecturally cannot: missing security controls, business logic flaws, attack-path chaining, and obfuscated secrets — with zero configuration.
18+
**Complements GitHub Advanced Security** by detecting what static tools architecturally cannot: missing security controls, business logic flaws, attack-path chaining, and obfuscated secrets — with zero configuration.
1919

2020
---
2121

2222
## Installation
2323

24-
### One-liner (recommended)
24+
### Manual (recommended)
2525

2626
```bash
27-
curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/claude-cybersecurity/main/install.sh | bash
27+
git clone https://github.com/AgriciDaniel/claude-cybersecurity.git
28+
cd claude-cybersecurity
29+
bash install.sh
2830
```
2931

30-
### Manual
32+
### Plugin (Claude Code native)
3133

3234
```bash
33-
git clone https://github.com/AgriciDaniel/claude-cybersecurity.git
34-
cd claude-cybersecurity
35-
bash install.sh
35+
claude plugin install cybersecurity
3636
```
3737

38-
### Windows (PowerShell)
38+
### One-liner (convenience)
3939

40-
```powershell
41-
irm https://raw.githubusercontent.com/AgriciDaniel/claude-cybersecurity/main/install.ps1 | iex
40+
```bash
41+
curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/claude-cybersecurity/main/install.sh | bash
4242
```
4343

4444
## Demo
@@ -79,10 +79,10 @@ https://youtu.be/aE295lLPO5A
7979
| Business logic flaw detection | No | Yes |
8080
| Authorization enforcement verification | Basic | Context-aware |
8181
| Race condition detection | Very limited | Concurrency pattern analysis |
82-
| Languages supported | 12 | 16+ (any language) |
82+
| Languages supported | 12 | 14 (pattern-based) + broader reasoning via LLM |
8383
| IaC/Container/CI-CD scanning | No | Terraform, Docker, K8s, Actions |
8484
| AI-generated code security | No | Specialized detection |
85-
| Obfuscated secret detection (84.4% recall) | Regex only | Semantic understanding |
85+
| Obfuscated secret detection | Regex only | Semantic context analysis |
8686
| Threat intelligence (malware/C2) | No | MITRE ATT&CK mapped |
8787
| Framework-aware false-positive suppression | No | 10 frameworks |
8888
| Cost | $49/committer/month | Free (with Claude Code) |
@@ -109,7 +109,7 @@ https://youtu.be/aE295lLPO5A
109109

110110
```
111111
skills/cybersecurity/
112-
├── SKILL.md (900 lines — orchestrator)
112+
├── SKILL.md (~990 lines — orchestrator)
113113
├── references/
114114
│ ├── vulnerability-taxonomy.md (25 CWE categories)
115115
│ ├── scoring-rubric.md (formula + confidence system)

0 commit comments

Comments
 (0)