Skip to content
Back to search

marketplace

Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/aiskillstore/marketplace with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/aiskillstore/marketplace'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/aiskillstore-marketplace/badge.svg)](/listings/aiskillstore-marketplace)

HTML

<a href="/listings/aiskillstore-marketplace"><img src="/api/listings/aiskillstore-marketplace/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

The recommended way to install any skill is the **`skillstore` CLI** — one command works for both **Claude Code** and **Codex**:

npx skillstore add author/skill-name

For example:

npx skillstore add aiskillstore/code-review

It downloads the skill and drops it into the right `skills/` directory for your tool. Claude Code auto-discovers it; for Codex, restart the session.

Prefer to do it by hand, or installing via Claude Web? See the full **[Installation Guides](https://skillstore.io/docs/install-guides)** for every method (CLI, manual, and ZIP upload) and the scope directories (`~/.agents/skills/`, `.claude/skills/`, `~/.claude/skills/`, `.codex/skills/`, …).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 90 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Skill Store — Marketplace Repository
  2. This is the open-source content repository behind
  3. **[Skill Store](https://skillstore.io)**. It stores every approved
  4. [Agent Skill](https://agentskills.io/specification), the records that go with
  5. it, and the automated security audits published with each skill.
  6. > **This repo is a companion to the Skill Store platform, not the place to submit skills.**
  7. > Skills are added through [skillstore.io](https://skillstore.io) — its review pipeline writes to this repo automatically. Please **do not open a pull request here to add a skill**; PRs adding skills will be closed. See [Contributing a skill](#contributing-a-skill) below.
  8. ## Installing a skill
  9. The recommended way to install any skill is the **`skillstore` CLI** — one command works for both **Claude Code** and **Codex**:
  10. ```sh
  11. npx skillstore add author/skill-name
  12. ```
  13. For example:
  14. ```sh
  15. npx skillstore add aiskillstore/code-review
  16. ```
  17. It downloads the skill and drops it into the right `skills/` directory for your tool. Claude Code auto-discovers it; for Codex, restart the session.
  18. Prefer to do it by hand, or installing via Claude Web? See the full **[Installation Guides](https://skillstore.io/docs/install-guides)** for every method (CLI, manual, and ZIP upload) and the scope directories (`~/.agents/skills/`, `.claude/skills/`, `~/.claude/skills/`, `.codex/skills/`, …).
  19. ## Contributing a skill
  20. Submit through the platform — not through a pull request:
  21. 1. Go to **[skillstore.io/submit](https://skillstore.io/submit)**.
  22. 2. Enter the GitHub repository URL that contains your `SKILL.md`.
  23. 3. Your submission runs through automated security analysis.
  24. 4. A maintainer reviews and approves it.
  25. 5. On approval, the skill is published here and appears on [skillstore.io](https://skillstore.io).
  26. ### What makes a valid skill
  27. - `SKILL.md` — the skill definition (**required**, per the [Agent Skills spec](https://agentskills.io/specification))
  28. - Supporting files the skill references (optional)
  29. - `LICENSE` (recommended)
  30. ### Security audit
  31. Every submission is scanned automatically before it can be published. The audit flags things like:
  32. - Dangerous code patterns (`eval`, `exec`, raw system commands)
  33. - File access outside the project scope
  34. - Network calls to external hosts
  35. - Obfuscated or minified code
  36. - Credential / secret handling
  37. Security analysis is report-only: findings inform maintainers and users, but a
  38. risk result does not automatically block an otherwise approved skill from being
  39. published. See our [Security Trust Center](https://skillstore.io/security) for
  40. the methodology, limitations, and risk-level definitions.
  41. Live Security Passport example:
  42. [![Skillstore security](https://skillstore.io/badges/skills/consiliency-research/security.svg)](https://skillstore.io/skills/consiliency-research?utm_source=security_passport_badge)
  43. ## Repository layout
  44. ```
  45. .
  46. ├── skills/ # Approved, published skills (one folder each, with SKILL.md)
  47. ├── pending/ # Submissions awaiting review
  48. ├── packages/
  49. │ ├── cli/ # The `skillstore` CLI (npx skillstore add …)
  50. │ └── skillstore/
  51. ├── schemas/ # JSON schemas for skill records
  52. ├── scripts/ # Maintenance & scoring scripts
  53. └── .github/workflows/ # Submission, audit, and sync automation
  54. ```
  55. The contents of this repo are maintained by Skill Store's automated pipeline. Manual changes are limited to maintainers.
  56. ## Links
  57. - **Website**: [skillstore.io](https://skillstore.io)
  58. - **Submit a skill**: [skillstore.io/submit](https://skillstore.io/submit)
  59. - **Install guides**: [skillstore.io/docs/install-guides](https://skillstore.io/docs/install-guides)
  60. - **Docs**: [skillstore.io/docs](https://skillstore.io/docs)
  61. - **Agent Skills spec**: [agentskills.io/specification](https://agentskills.io/specification)
  62. ## License
  63. The marketplace catalog is MIT-licensed. Individual skills carry their own licenses — check each skill's `LICENSE` file.
skills/0xdarkmatter/claude-code-templates/assets/hook-script.sh · Bundled script · 85 lines · 1 finding marked
  1. #!/bin/bash
  2. #
  3. # Claude Code Hook: [Description]
  4. #
  5. # Event: [PreToolUse|PostToolUse|SessionStart|etc]
  6. # Matcher: [Tool name or * for all]
  7. #
  8. # Security: Validates input, quotes variables, prevents path traversal
  9. #
  10. set -euo pipefail
  11. # Error handling
  12. trap 'echo "Error at line $LINENO" >&2; exit 1' ERR
  13. # Check dependencies
  14. command -v jq >/dev/null 2>&1 || {
  15. echo "jq is required but not installed" >&2
  16. exit 1
  17. }
  18. # Read input from stdin
  19. INPUT=$(cat)
  20. # Validate JSON
  21. if ! echo "$INPUT" | jq -e '.' > /dev/null 2>&1; then
  22. echo "Invalid JSON input" >&2
  23. exit 2
  24. fi
  25. # Parse common fields
  26. TOOL=$(echo "$INPUT" | jq -r '.tool_name // empty')
  27. SESSION=$(echo "$INPUT" | jq -r '.session_id // empty')
  28. # -------------------------------------------------------------------
  29. # Your hook logic here
  30. # -------------------------------------------------------------------
  31. # Example: Log tool usage
  32. LOG_FILE="${CLAUDE_PROJECT_DIR:-.}/.claude/hook.log"
  33. mkdir -p "$(dirname "$LOG_FILE")"
  34. echo "$(date -u +"%Y-%m-%dT%H:%M:%SZ") | $TOOL | $SESSION" >> "$LOG_FILE"
  35. # Example: Block dangerous operations
  36. # if [[ "$TOOL" == "Bash" ]]; then
  37. # CMD=$(echo "$INPUT" | jq -r '.tool_input.command // empty')
  38. # if [[ "$CMD" == *"rm -rf /"* ]]; then
    • Note: Quoted as data in code: Runs `rm -rf` against a root or home-directory path
    • Line 47 on GitHub
  39. # echo "Blocked dangerous command" >&2
  40. # exit 2 # Exit 2 = blocking error
  41. # fi
  42. # fi
  43. # Example: Validate file paths
  44. # if [[ "$TOOL" == "Write" ]]; then
  45. # FILE=$(echo "$INPUT" | jq -r '.tool_input.file_path // empty')
  46. # if [[ "$FILE" == *".."* ]]; then
  47. # echo "Path traversal blocked" >&2
  48. # exit 2
  49. # fi
  50. # fi
  51. # -------------------------------------------------------------------
  52. # Exit codes:
  53. # 0 = Success (continue execution)
  54. # 2 = Blocking error (stderr shown to Claude)
  55. # Other = Non-blocking error (logged, continues)
  56. # -------------------------------------------------------------------
  57. exit 0
  58. # CONFIGURATION EXAMPLE:
  59. # Add to ~/.claude/settings.json or .claude/settings.local.json:
  60. #
  61. # {
  62. # "hooks": {
  63. # "PreToolUse": [{
  64. # "matcher": "*",
  65. # "hooks": [{
  66. # "type": "command",
  67. # "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/this-script.sh",
  68. # "timeout": 5000
  69. # }]
  70. # }]
  71. # }
  72. # }
skills/92bilal26/code-validation-sandbox/scripts/setup-sandbox.sh · Bundled script · 91 lines · 1 finding marked
  1. #!/bin/bash
  2. # setup-sandbox.sh - Create persistent validation container
  3. # Part of code-validation-sandbox v3.0 (Reasoning-Activated)
  4. set -euo pipefail
  5. CONTAINER_NAME="code-validation-sandbox"
  6. BASE_IMAGE="${1:-python:3.14-slim}"
  7. echo "=== Code Validation Sandbox Setup ===" >&2
  8. echo >&2
  9. # Check if container already exists
  10. if docker ps -a --format '{{.Names}}' | grep -q "^${CONTAINER_NAME}$"; then
  11. echo "Container '$CONTAINER_NAME' already exists" >&2
  12. # Check if running
  13. if docker ps --format '{{.Names}}' | grep -q "^${CONTAINER_NAME}$"; then
  14. echo "✅ Container is running" >&2
  15. container_id=$(docker ps --filter "name=$CONTAINER_NAME" --format '{{.ID}}')
  16. echo "Container ID: $container_id" >&2
  17. exit 0
  18. else
  19. echo "Container exists but is stopped. Starting..." >&2
  20. docker start "$CONTAINER_NAME" >&2
  21. echo "✅ Container started" >&2
  22. exit 0
  23. fi
  24. fi
  25. echo "Creating new container with base image: $BASE_IMAGE" >&2
  26. echo >&2
  27. # Create persistent container
  28. container_id=$(docker run -d \
  29. --name "$CONTAINER_NAME" \
  30. --mount type=bind,src="$(pwd)",dst=/workspace \
  31. "$BASE_IMAGE" \
  32. tail -f /dev/null)
  33. echo "Container created: $container_id" >&2
  34. echo >&2
  35. # Install base tools
  36. echo "Installing base tools..." >&2
  37. docker exec "$CONTAINER_NAME" bash -c "
  38. set -e
  39. apt-get update -qq
  40. apt-get install -y -qq curl git build-essential > /dev/null 2>&1
  41. echo '✓ Base tools installed'
  42. "
  43. # Install Python tools (if Python base image)
  44. if [[ $BASE_IMAGE == python:* ]]; then
  45. echo "Installing Python tools..." >&2
  46. docker exec "$CONTAINER_NAME" bash -c "
  47. set -e
  48. # Install UV package manager
  49. curl -LsSf https://astral.sh/uv/install.sh | sh > /dev/null 2>&1
  50. export PATH=\"\$HOME/.cargo/bin:\$PATH\"
  51. # Install common Python tools
  52. pip install --quiet pytest mypy ruff 2>/dev/null
  53. echo '✓ Python tools installed (UV, pytest, mypy, ruff)'
  54. "
  55. fi
  56. # Install Node.js (for multi-language support)
  57. echo "Installing Node.js..." >&2
  58. docker exec "$CONTAINER_NAME" bash -c "
  59. set -e
  60. curl -fsSL https://deb.nodesource.com/setup_20.x | bash - > /dev/null 2>&1
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 75 on GitHub
  61. apt-get install -y -qq nodejs > /dev/null 2>&1
  62. npm install -g pnpm > /dev/null 2>&1
  63. echo '✓ Node.js 20 + pnpm installed'
  64. "
  65. echo >&2
  66. echo "=== Setup Complete ===" >&2
  67. echo "Container: $CONTAINER_NAME" >&2
  68. echo "ID: $container_id" >&2
  69. echo >&2
  70. echo "Installed:" >&2
  71. echo " - Python 3.14 + UV + pytest + mypy + ruff" >&2
  72. echo " - Node.js 20 + pnpm" >&2
  73. echo " - Base tools (curl, git, build-essential)" >&2
  74. echo >&2
  75. echo "✅ Sandbox ready for validation" >&2

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.