pentest-tools
zhaoxuya520
Find and verify flaws in authorized targets.
Penetration testing
SE
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.- 1.5k
- 1.5k
reverse-engineering
zhaoxuya520
Understand what hidden code in binaries does.
Reverse engineering
DO 
1.5kjwt-security
mindrally
Build JWT authentication with safer defaults.
Authentication security
1.5kqwencloud-ops-auth
qwencloud
Get your QwenCloud API authentication working.
API authentication
+1
1.5kllm-security
semgrep
Catch security risks in your LLM applications.
Application security
- 1.5k
apk-reverse
zhaoxuya520
Find the key logic inside your Android apps.
Mobile reverse engineering
1.5kiam-helper-for-troubleshooting
google
Find what's blocking your Google Cloud access.
Access management
- 1.4k
iam-helper-for-policy-management
google
Manage who can access your Google Cloud resources.
Access management
1.4kauth
adobe
Get an admin login token for AEM Edge Delivery Services.
Admin authentication
AE- 1.4k
mantis-review
google
Separate real code flaws from false alarms.
Security review
- 1.4k
mantis-summarize
google
Map your codebase before a security review.
Security review
- 1.4k
mantis-architecture
google
Your codebase, mapped with its security history.
Security architecture
1.4kandroid-intent-security
android
Harden your Android app against unsafe intents.
Mobile application security
- 1.4k
mantis-critic
google
Find which security flaws survive a release build.
Security assessment
- 1.4k
mantis-plan
google
A security review roadmap for your codebase.
Security review
- 1.4k
mantis-researcher
google
Find security flaws across your code's callers.
Code security
- 1.4k
mantis-report
google
Turn security findings into a shareable review.
Security reporting
1.4kstride-threat-modeling
securityskills
Turn system designs into ranked security risks.
Threat modeling
- 1.4k
mantis-dedupe
google
Raw security findings, without duplicate reports.
Security review
1.4kthreat-modeling-with-aws-security-agent
aws
Find security risks in specs against your code.
Threat modeling
+1- 1.4k
mantis-reproduce
google
Verify security flaws with sandboxed crash tests.
Security testing
- 1.4k
pentesting-with-aws-security-agent
aws
Find live app flaws with AWS Security Agent.
Penetration testing
+1 - 1.4k
mantis-calibrate
google
Rank security findings by evidence and impact.
Security risk assessment
1.4ksecurity
boshu2
Find security flaws without hiding review gaps.
Security review
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.