vuln-scan
anthropics
Find security bugs in your code without running it.
Security code review
Security skills for AI agents
These Skills look at software the way an attacker or an auditor would. The biggest groups review code for injection and broken access rules, probe systems in penetration tests and audit cloud accounts against best practices; smaller sets cover sign-in, malware analysis and forensics.
Sort by
Most installed
794 Skills
Showing Skills in Security.- 1.1k
1.1kclaims
ruvnetControl what your agents are allowed to do.
Access control
CF
1.1kautopentestx-automated-pentesting
reason-machines
Find security flaws in hosts and get a report.
Penetration testing
+1- 1.1k
malware-detection-awareness
reason-machines
Spot risky software before you trust a download.
Software security
1.1ksumsub-api-auth
sumsub
Get working, signed requests to the Sumsub API.
API authentication
1.1knextauth-authentication
mindrally
Build secure sign-in for your Next.js app.
Web authentication
- 1.1k
slowmist-agent-security-framework
reason-machines
Spot security risks before trusting external tools.
Security review
+1 - 1.1k
sumsub-create-poa-preset
sumsub
Set which address documents Sumsub accepts.
Identity verification
- 1.1k
sumsub-integrate-websdk
sumsub
Add identity checks to your website with Sumsub.
Identity verification
- 1.1k
patch
anthropics
Candidate security fixes for human review.
Security remediation
- 1.1k
triage
anthropics
Turn scanner findings into a ranked fix list.
Security triage
- 1.1k
avast-premium-security-analysis
reason-machines
Understand how Avast protects against malware.
Security research
- 1.1k
malware-warning-avast-keygen
reason-machines
Spot the risks in an Avast keygen repository.
Software security
1.1kmobile-reverse
zhaoxuya520
Inspect Android and iOS apps for security gaps.
Mobile application security
- 1.1k
sumsub-create-level
sumsub
Create Sumsub verification flows in a sandbox.
Identity verification
- 1.1k
sumsub-create-cross-check-preset
sumsub
Custom name and address checks for Sumsub.
Identity verification
- 1.1k
sumsub-create-questionnaire
sumsub
Build Sumsub questionnaires in your sandbox.
Identity verification
- 1.1k
palisade-security-nexus-bitdefender
reason-machines
Set up BitDefender protection for your computer.
Endpoint security
+1 - 1.1k
malware-warning-avast-piracy
reason-machines
Avoid unsafe Avast downloads and find safe sources.
Software security
1.1kagent-supply-chain
github
Catch changed files in your agent plugins.
Supply chain security
- 1.1k
avast-security-awareness
reason-machines
Spot malware disguised as antivirus downloads.
Software security
- 1.1k
report-malicious-repository
reason-machines
Spot fake security tools in GitHub repositories.
Repository security
1.1kvtex-io-auth-and-policies
vtex
Keep your VTEX IO app permissions narrowly scoped.
Application authorization
- 1.1k
wxmini-security-audit
reason-machines
Find security flaws in your WeChat mini-program.
Application security
A Skill only gives the agent instructions and tools; it carries no permission of its own. Penetration testing and reverse engineering Skills are written for systems you own or are authorised to test, and the agent works with the access you give it.
A review reads the code or configuration and points out weaknesses. A penetration test runs the system and tries to exploit them, which shows whether a weakness can actually be used.
Tests check that the code does what it should; security Skills check what it should never do, such as letting one user read another's data. The two catch different mistakes.