Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →evolutionunleashed/skill-sentinel
Security scanner and threat analyzer for AI agent skills. Activate this skill whenever a new skill is added to the workspace, when the user imports or installs a skill from an external source, when asked to audit or review an existing skill for safety, or when the user mentions scanning, vetting, checking, or validating a skill before use. Also trigger when the user references skill security, malicious code detection, prompt injection scanning, or supply chain safety for any SKILL.md file or ski
Passed 17 of 22 test cases with the skill, and 15 of 22 without it.
2 fixed15 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
A complete review of a read-only formatting skill reveals zero findings across all eight threat categories. Determine the overall risk rating for the report header.
| Checked | Without skill | With skill |
|---|---|---|
| The response assigns CLEAN as the overall risk rating when zero findings are detected across all categories | Missed | Passed |
The instructions your model reads when the skill loads.
Security analysis engine for detecting malicious code, prompt injection, data exfiltration, and supply chain threats in AI agent skills before they execute in your environment.
The agent skills ecosystem has a supply chain problem. Snyk's ToxicSkills research found that 13.4% of skills on public registries contain critical security issues. Cisco identified 341 malicious skills in a single audit. Skills operate with the full permissions of the agent they extend, meaning a compromised skill inherits access to your filesystem, credentials, environment variables, and network connectivity. This scanner catches threats before they execute.
When triggered, follow this sequence exactly.
Determine which skill needs scanning. The user will either specify a path directly or reference a skill by name. If the target is ambiguous, ask once for clarification. Confirm the skill directory path before proceeding.
Read the complete contents of every file in the skill directory and any subdirectories. This includes SKILL.md, any referenced scripts, configuration files, agent definitions, helper files, and knowledge documents. Record the total file count and types discovered.
Do not skip any file. Malicious payloads frequently hide in auxiliary files rather than the main SKILL.md to evade casual review. The ClawHavoc campaign specifically exploited this pattern by placing exfiltration code in referenced helper scripts while keeping the primary skill description clean.
Analyze every file against all eight threat categories defined below. Each category operates independently with its own detection criteria. Process them sequentially and document findings per category.
test cases passed, vs 15 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.