For scanning agent skills for security issues, the most directly matching sources are SkillsSafe, a free scanner for SKILL.md, MCP configs and system prompts 5, and SkillTotal, a static scanner for MCP servers and agent skills that reports file:line evidence 6. Broader code-security options such as Semgrep 3 and Sentry's skill-scanner action 1 are also relevant.
- 1
SkillsSafe AI Skill Security Scannerskillssafe.comwebsite read, tools not yet checked
Scans SKILL.md files, MCP configs and system prompts for credential theft, data exfiltration, shell injection and prompt injection before installation 5.
official:MCP server · SkillsSafe Security Scanner+1 community tools built for it
- 2
SkillTotalskilltotal.aiwebsite read, tools not yet checked
Free static scanner for agent skills and MCP servers that finds prompt injection, tool poisoning and exfiltration with file:line evidence 6.
official:MCP server · SkillTotal+1 community tools built for it
- 3
Sentrysentry.ioverified and signed
Its skill-scanner action scans agent skills for security issues and checks them for injection, per its action record 11.
official:MCP server · @sentry/mcp-serverSDK · @sentry/nodeCLI · sentry-clirepository · sentry-pythonskill · sentry-cli+49 community tools built for it
for agents: skill-scanner · skill-writer · sentry-sdk-skill-creator
- 4
Semgrep App Security Platformsemgrep.devverified and signed
Its semgrep action runs static analysis scans to find security vulnerabilities in code, and its llm-security guidance covers LLM application security 13.
+4 community tools built for it
for agents: code-security · llm-security · semgrep
Sources
- 1Sentry Docs | Application Performance Monitoring & Error Tracking Softwaredocs.sentry.io · read 2026-10-29
- 3Semgrep App Security Platform | AI-assisted SAST, SCA and Secrets Detectionsemgrep.dev · read 2026-10-29
- 5SkillsSafe — Free AI Skill Security Scanner | Check Before You Installskillssafe.com · read 2026-10-29
- 6MCP Server & Agent Skill Security Scanner · SkillTotalskilltotal.ai · read 2026-10-29
- 11skill-scanner: declares "skill-scanner" (the record we read and signed)unfragile.ai · read 2026-10-24
- 13code-security: declares "code-security" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
skill-scanner · skill-scanner verified and signed
Scan agent skills for security issues. Use when asked to "scan a skill", "audit a skill", "review skill security", "check skill for injection", "validate SKILL.md", or assess whether an agent skill is safe to install. Checks for prompt injection, malicious scripts, excessive permissions, secret expo
claude-security/skill/claude-security · claude-security verified and signed
Skill claude-security (in the claude-security plugin)
code-security · code-security verified and signed
Security guidelines for writing secure code. Use when writing code, reviewing code for vulnerabilities, or asking about secure coding practices like 'check for SQL injection' or 'review security'. IMPORTANT: Always consult this skill when writing or reviewing any code that handles user input, authen
docker-sandboxes-kits · docker-sandboxes-kits verified and signed
Use this skill when authoring, validating, packaging, signing, or composing a Docker Sandboxes kit `spec.yaml` (`sbx kit add/inspect/pack/pull/push/sign/validate/verify`), even if the user just says they want to "add a tool to a sandbox agent", "build a reusable sandbox extension", "publish a kit to
· SkillsSafe website read, tools not yet checked
Free security scanner for AI agent skills. Scan any SKILL.md, MCP config, or system_prompt for credential theft, data exfiltration, and prompt injection. Supports OpenClaw, Claude Code, Cursor, Codex. No signup required.
· SkillTotal website read, tools not yet checked
Free static scanner for MCP servers, agent skills and npm/PyPI packages. Finds prompt injection, tool poisoning and exfiltration with file:line evidence.
skill-creator · skill-creator verified and signed
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) upd
rc-security · rc-security verified and signed
Use this skill when hardening a RevenueCat integration on Android. Covers Trusted Entitlements response verification (INFORMATIONAL vs ENFORCED), why the server is always the authority, API key hygiene (public SDK key vs secret REST key), anonymous user identity, and purchase token protections Reven
make-skill-template · make-skill-template verified and signed
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory struct
skill-creator · skill-creator verified and signed
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.