secure-ai-agent-coding
Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls.
Skill by jpcaparas
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jpcaparas-secure-ai-agent-coding
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, data, ml, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/secure-ai-agent-coding
What's inside
- Skill name
secure-ai-agent-coding- Description
- Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec.
- License
- unknown
- Compatibility
- Requires: python3 for optional local pattern scanning. No external packages required.
- Metadata
- version: 1.0.0 · short-description: Secure AI agent coding review and hardening
- Instructions
- 85 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (20)
- AGENTS.md
- README.md
- SKILL.md
- .gitkeep · agents/
- .gitkeep · assets/
- evals.json · evals/
- metadata.json
- controls.md · references/
- gotchas.md · references/
- governance.md · references/
- implementation-patterns.md · references/
- review-workflow.md · references/
- source-policy.md · references/
- threat-model.md · references/
- scan_patterns.py · scripts/
- test_skill.py · scripts/
- validate.py · scripts/
- skill-card.png
- skill-card.prompt.md
- security-review.md · templates/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from jpcaparas/skills
- 0.595score
azure-devops-wiki-markdown
jpcaparas
Write, fix, or review Azure DevOps wiki Markdown, Mermaid, _TOC_, _TOSP_, details blocks, query tables, mentions, work-item links, KaTeX, videos, and code…
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
zoom-out
jpcaparas
Map unfamiliar code one layer up: modules, callers, callees, entrypoints, boundaries, dependencies, and data flow.
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
zai-search
jpcaparas
Searches the web, reads pages, and searches GitHub repositories through Z.ai (Zhipu GLM) tools using Z_AI_API_KEY: web search, web reader, and Zread over MCP…
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
adversarial-test-sweep
jpcaparas
Run a bounded adversarial sweep of an existing test suite.
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
isitagentready
jpcaparas
Audit a repo against Cloudflare/isitagentready signals for AI agent readiness: robots.txt, llms.txt, Markdown negotiation, MCP/API catalogs, OAuth discovery…
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
ripgrep
jpcaparas
Uses ripgrep (`rg`) for local text and path search, including code symbols, literals, regexes, filename discovery, and machine-readable matches.
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
implicit-token-savings
jpcaparas
Selects sufficient, low-noise local shell commands for repository exploration, git inspection, tests, and container checks.
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
gemini-search
jpcaparas
Grounded Google Search, URL reading, and gated Deep Research via Gemini (GEMINI_API_KEY).
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
nanobanana
jpcaparas
Generates and edits images with Google's Nano Banana, pinned to Gemini Nano Banana 2.1, via GEMINI_API_KEY: text-to-image, photo edits, multi-reference…
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
nanobanana-infographic
jpcaparas
Create infographic prompts and render workflows with Nano Banana 2.1, with adaptable low-noise presets for posts, decks, reports, and explainers.
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
preventing-ui-slop
jpcaparas
Prevents generic, decorative AI UI defaults.
SkillAFreshness: A★ 55Claude Code +9 - 0.593score
maintainable-code
jpcaparas
Guide maintainable, resilient, test-double-friendly code: clear names, decomposition, safe defaults, idempotency, bounded retries, observability, and quality…
SkillAFreshness: A★ 55Claude Code +9
Signals
- Stars
- 55
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Oct 18, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- License unknown
- Repository
- github.com/jpcaparas/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jpcaparas
- 0.597score
laravel:request-forgery-protection
jpcaparas
Configure CSRF and origin-aware request forgery protection; PreventRequestForgery middleware (Laravel 13+) with token fallback and exclusions
SkillCFreshness: C★ 157Claude Code +9 - 0.597score
laravel:code-review-requests
jpcaparas
Request effective code reviews—specify focus areas, provide context, ask for architectural feedback, reference Laravel conventions
SkillCFreshness: C★ 157Claude Code +9 - 0.597score
laravel:debugging-prompts
jpcaparas
Create effective debugging prompts—include error messages, stack traces, expected vs actual behavior, logs, and attempted solutions
SkillCFreshness: C★ 157Claude Code +9 - 0.597score
laravel:effective-context
jpcaparas
Provide comprehensive context in prompts—files, errors, Laravel version, dependencies, and monorepo details—for accurate AI responses
SkillCFreshness: C★ 157Claude Code +9 - 0.597score
laravel:ai-sdk
jpcaparas
Build AI features with the first-party Laravel AI SDK (Laravel 13+); agents, embeddings, images, audio, and tool calling with provider-agnostic APIs
SkillCFreshness: C★ 157Claude Code +9 - 0.597score
laravel:eloquent-relationships
jpcaparas
Define clear relationships and load data efficiently; prevent N+1, use constraints, counts/sums, and pivot syncing safely
SkillCFreshness: C★ 157Claude Code +9
Cite this page
secure-ai-agent-coding skill. Agent Mart. https://agentmart.dev/skills/jpcaparas-secure-ai-agent-coding (last updated 2026-10-24)