← Back to home
Agent Skill Security Scanner
An agent skill — a SKILL.md plus its bundled scripts — runs inside your agent with its permissions. Paste its repository URL or package on the home page, or upload the skill folder as a ZIP, and see what its code actually does — and whether it exceeds what it declares — before you install it.
Scan a component — free →Skill-specific risks it catches
- Undeclared capabilities: the skill's
allowed-toolssay one thing, but the bundled code shells out, reaches the network, or writes files anyway — a least-privilege violation. - Hidden instructions: prompt-injection or tool-poisoning text in
SKILL.mdthat steers your agent — caught even behind look-alike or zero-width characters. - Dangerous bundled scripts: shell/exec, credential-path access, or decode-and-run payloads in the scripts shipped alongside the skill.
Evidence, not guesswork
Detection is deterministic (regex + AST), your code is never executed, and every finding points at the exact file and line. The declared-vs-actual check is structural — it compares the skill's own declaration to what the code does, with no LLM inferring intent.
Scanned agent skills
- Last30Days SkillLOW
- Frontend SlidesLOW
- Drawio SkillLOW
- Guizang Social Card SkillLOW
- Obsidian Second BrainLOW
- Agents Best PracticesLOW
- ArchifyLOW
- Video Podcast MakerLOW
- NopuaLOW
- Karpathy Llm WikiLOW
- Boss Agent CliLOW
- Pixel2MotionLOW
- Claude BlogMALICIOUS
- Zhengxi ViewsLOW
- Gpt Image2 Ppt SkillsLOW
- User Research SkillLOW
- HueLOW
- Agentic Seo SkillLOW
- StorybloqLOW
- ShuorenhuaLOW
- Web DesignLOW
- Bazi Ziwei SkillLOW
- Compose SkillLOW
- Claude Skill Social PostLOW
- Vibe CheckLOW
- ClaudeforgeLOW
- Claude Code Aso SkillLOW
Learn it hands-on
Try the interactive prompt injection lab to make a guarded agent leak its secret — then see the defenses.
FAQ
- What is an agent skill?
- An Anthropic Agent Skill is a folder with a SKILL.md (instructions plus frontmatter) and optional bundled scripts/resources, loaded by agents such as Claude Code, Gemini CLI and others. It runs with your agent's permissions.
- What does “undeclared capability” mean?
- A SKILL.md can declare allowed-tools — a least-privilege list. If the bundled code uses a capability those tools do not grant (for example it runs a shell while declaring only Read), SkillTotal flags the mismatch.
- How do I scan a skill — and does it run the skill?
- Nothing is installed or executed; analysis is fully static. Paste the skill's GitHub/GitLab repo URL (or npm/PyPI package) on the home page, or zip the skill folder and upload it on the Scan a skill or project page.