clawheart-security
1561Skill Claude CodeCodex
A skill for using the local ClawHeart command-line tool to audit AI security, evaluate skills, and manage agent credentials.
not rated 4 4mo ago B 58 tokens
odoo-code-review
1562Immoderate-humulin783/odoo-skills
Skill Claude CodeCodex
Review Odoo addon code for correctness, security, performance, migrations, tests, and official Odoo coding guidelines. Use when reviewing Odoo modules, diffs, pull requests, or changed files involving models, fields, XML views, data, controllers, reports, OWL/assets, manifests, access rules, record rules, or OCA…
not rated 4 24d ago A 75 tokens
audit-release-gate
1563beriktassuly/solana-audit-skill
Command Claude Code
Produce a machine-readable Solana release gate using the solana-audit release workflow and evidence-backed PASS, FAIL, or SKIP checks.
not rated 4 4mo ago A 33 tokens
original MIT
gaia
1564Plugin Claude Code
Bundles 39 skills, 9 agents, 12 hooks · 2,227 tokens together
GAIA — Generative AI Interface for Agents. Security-first multi-agent orchestration for Claude Code and OpenCode: reads run free, state changes need approval, irreversible ops blocked.
not rated 4
changed 22d ago A
tokens not measured
original MIT
ai-security-review
1565Skill Claude CodeCodex
Use this skill to audit an AI system for security vulnerabilities including prompt injection, sensitive data exposure, excessive agent permissions, unsafe tool calls, and insecure output handling. Grounded in OWASP GenAI LLM Top 10 (2026). Activates before production deployment of any LLM-based application, agent, or…
not rated 4 8d ago A 74 tokens
nextjs
1566kristiyan-velkov/ai-security-rules
Cursor rule Cursor
Next.js security (next.js app).
not rated 4 21d ago A 0 tokens
agentseal-mcp-intel
1567getagentseal/agentseal-mcp-intel
MCP server Claude CodeCodexCursor +2
MCP server for AgentSeal — find safe MCP servers, check security before installing, and scan your AI dev environment from inside your AI coding assistant. Runs locally from the agentseal-mcp-intel npm package.
not rated 4 7mo ago A
tokens not measured
krakend-ai-assistant
1568Plugin Claude Code
Bundles 5 skills, 1 agent, 1 MCP server · 176 tokens together
AI assistance for KrakenD API Gateway configuration, validation, security auditing, and Flexible Configuration support.
not rated 4
changed 7d ago A
tokens not measured
original Apache-2.0
shuttle-mcp
1569MCP server Claude CodeCodexCursor +2
Secure SSH gateway for AI assistants — MCP server with connection pooling, session isolation, and command safety. Runs locally from the shuttle-mcp Python package.
not rated 4 2mo ago A
tokens not measured
original MIT
openvas-mcp
1570MCP server Claude CodeCodexCursor +2
MCP server "openvas-mcp" as configured in CyberSecAuto-Labs/OpenVAS-MCP. Runs locally from the openvas-mcp Python package.
not rated 4 1mo ago A
tokens not measured
original Apache-2.0
fuzzmind-frida-mcp
1571MCP server Claude CodeCodexCursor +2
Frida MCP server for authorized dynamic analysis and application security research. Runs locally from the fuzzmind-frida-mcp Python package.
not rated 4 6mo ago A
tokens not measured
original MIT
read-no-evil-mcp
1572MCP server Claude CodeCodexCursor +2
A secure email gateway MCP server that protects AI agents from prompt injection attacks in emails. Runs locally from the read-no-evil-mcp Python package.
not rated 4 7mo ago A
tokens not measured
original Apache-2.0
aegis-mcp
1573MCP server Claude CodeCodexCursor +2
A deterministic MCP server that maps threat-model context to actionable coding requirements. Runs locally from the aegis-mcp Python package.
not rated 4 3mo ago A
tokens not measured
original MIT
agent-passport-mcp
1574MCP server Claude CodeCodexCursor +2
Cryptographic identity, delegation, governance, and commerce for AI agents. 152 tools. Runs locally from the agent-passport-system-mcp npm package.
not rated 4 1mo ago A
tokens not measured
original Apache-2.0
hunter
1575Skill Claude CodeCodex
Use for authorized web/API security assessment, CTF vulnerability research, Hunter health checks, MCP orchestration, local knowledge-base lookup, evidence registration, and report generation. All HTTP tools go through RequestBroker — WAF blocks, captchas, and rate limits never produce false findings.
not rated 4 3mo ago A 58 tokens
GPL-3.0
secrets-management
1576Skill Claude CodeCodex
Use when the user asks to "store a secret", "fetch credentials", "rotate an API key", "manage secrets", "set up vault access", or any task involving secure credential storage and retrieval.
not rated 4 yesterday A 0 tokens
original MIT
sast-mcp-server
1577MCP server Claude CodeCodexCursor +2
A standard MCP server for SAST/DAST tools (Bandit, njsscan, Bearer, Semgrep, Trivy, CodeQL, Checkov, Gitleaks, OSV-Scanner, Grype, OWASP ZAP) — scan code for security vulnerabilities from any AI agent. Runs locally from the sast-mcp-server Python package. Needs 4 environment variables to run.
not rated 4 4mo ago A
tokens not measured
original MIT
enil-ling-pesing
1578Skill Claude Code
A Chinese-language guide for authorized penetration testing and security research. Penetration testing is controlled testing used to find security weaknesses in software or systems.
not rated 4
changed 9d ago A 192 tokens
original MIT
arcjet
1579Skill Claude CodeCodex
Add Arcjet security protection to HTTP routes, AI agent tool calls, MCP servers, background jobs, and queue workers. Covers rate limiting, bot detection, email validation, prompt injection, sensitive information blocking (including Rampart NER), content moderation, capture/flush, remote Guard policies, typed inputs…
not rated 4
changed 1mo ago A Socket: passSnyk: pass 198 tokens
original Apache-2.0
Skill Claude CodeCodex
Reviews an existing MOSS wallet integration for security and correctness before launch on MegaETH. Use when auditing partner code rather than building it: produces findings grouped as Critical, Risky defaults, and Recommendations with concrete remediations. Checks for frontend-owned trust decisions, missing backend…
not rated 4 2mo ago A 127 tokens
fable-audit
1581Skill Claude CodeCodex
Evidence-first codebase audit for correctness, security, privacy, data, integration, operational, test, and docs-vs-reality risks. Use when the user asks for a Fable-5 audit, exhaustive audit, bug hunt, risk review, codebase audit, security/integration audit, or asks Codex to find issues before changing code.
not rated 4
changed 17d ago A 75 tokens
original MIT
mcp-redteam
1582Plugin Claude Code
Bundles 1 skill · 31 tokens together
Full audit and penetration testing of MCP servers — health, architecture, completeness, security.
not rated 4
changed 1mo ago A
tokens not measured
original MIT
salingnh/android-reverse-engineering-mcp
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 56 tokens together
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
not rated 4
changed 2mo ago A
tokens not measured
original Apache-2.0
Skill Claude CodeCodex
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct…
not rated 4 3mo ago A 105 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: