secure-code
v1.0.0by sekar3s · author: OctoCAT Platform Team
Security guardian: blocks secrets and dangerous commands before they land, scans for OWASP Top 10 patterns, and guides fast, minimal fixes so code ships safely.
Package we checked
The manifest we fetched is plugins/secure-code/plugin.json in sekar3s/octocat-agent-plugins-demo. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 1 skill (secure-code-review) and 1 MCP server (vuln-scout). Stored mcp.json transports: vuln-scout stdio.
What secure-code does, in the publisher's words
Security guardian that helps you ship faster. It blocks hard-coded secrets and destructive commands before they land, flags OWASP Top 10 patterns as code is written, audits your supply chain, and guides minimal, tested fixes.
> These rules are fast, offline heuristics for the inner loop. They complement, and don't replace, GitHub code scanning (CodeQL), Dependabot, and secret scanning with push protection.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 1
- MCP servers
- 1
- Stars
- 0
- License
- MIT
- Repo created
- 2026-09-29
- Last pushed
- 2026-10-14
- Publisher type
- User
- Version
- 1.0.0
Links
Skills · 1
- secure-code-review
- Security review for code changes or a whole repository, finds hard-coded secrets, OWASP Top 10 / CWE-mapped vulnerabilities (SQL injection, XSS, command injection, weak crypto, TLS bypass, permissive CORS), and supply-chain risks, then proposes minimal fixes. Use when the user asks for a security r…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- vuln-scoutstdio
- node ${PLUGIN_ROOT}/servers/vuln-scout.mjs
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
security · appsec · owasp · secrets · cwe · devsecops
Related by publisher and keywords
Security guardrails for AI agents: blocks destructive commands and secret access with hooks, scans for secrets and vulnerable dependencies (OSV.dev) via MCP, and adds a security-reviewer agent and threat-model skill.
Onboard to any codebase in minutes: an onboarding-guide agent, a codebase-tour skill that writes ONBOARDING.md, a session hook that maps the repo automatically, and the Microsoft Learn MCP server for trusted platform docs.
Day-one onboarding mentor: maps the codebase, verifies your toolchain, finds setup steps and code owners, and suggests a first task so new engineers are productive on day one.
Release-readiness toolkit: scores your repo 0-100 via MCP, drafts audience-friendly release notes with a skill, recommends the next semantic version, and audits every agent tool call with hooks.
Release-readiness copilot: go/no-go checks, semver suggestions, changelog drafts, and guardrails for risky release commands.
Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
[](https://agentpluginsdirectory.com/plugins/secure-code)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.