github-actions-hardening
github
Find CI security risks with fixes you can review.
CI security
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.- 1.7k
1.7kmapbox-token-security
mapbox
Keep your map tokens restricted and safely managed.
Access token security
1.7krev-dex-dumper
p4nda0s
Recover decrypted DEX files from a running Android app.
Reverse engineering
- 1.7k
rev-idapython
p4nda0s
Write scripts to inspect, debug, and decompile binaries.
Reverse engineering
1.7kinvestigate-anything
useosint
Turn a vague investigation into a defensible answer.
Open-source intelligence
1.7kaws-secrets-manager
aws
Use secrets without putting plaintext in the agent's context.
Secret management
1.7kn8n-credentials-and-security-official
n8n-io
Keep n8n workflow secrets out of plain text.
Workflow security
- 1.7k
find-leaks-in-the-wild
useosint
Find circulating leaks and separate breaches from recycled data.
Breach investigation
1.7kclawhub-skill-vetting
hugomrtz
Know the risks before installing a skill.
Software security
1.7kshannon-ai-pentester
reason-machines
Get reproducible exploits and an actionable audit report.
Application security
+2- 1.6k
rev-u3d-dump
p4nda0s
Recover names and types from Unity binaries.
Reverse engineering
- 1.6k
anthropic-cybersecurity-skills
reason-machines
Find the right workflow for each security operation.
Security operations
1.6kowasp-security-check
sergiodxa
Find security flaws and get prioritized fixes.
Application security
- 1.6k
google-like-a-spy
useosint
Find overlooked documents and mentions with precise searches.
Open-source intelligence
1.6kusing-sops
jssblck
Manage encrypted secrets with the right keys.
Secrets management
+2
1.6kmantis-threat-model
google
Turn your architecture knowledge into a threat model.
Threat modeling
1.6kintended-vs-implemented
phuryn
Find where your code breaks its documented rules.
Security auditing
- 1.6k
dpop-adoption
google
Build key-bound refresh tokens with clear security rules.
Identity security
1.6kconvex-security-audit
waynesutton
Know who can reach your backend and what to fix.
Backend security
1.6kclaude-security
anthropics
Find vulnerabilities and get reviewed fixes you choose to apply.
Application security
1.6krust-review
trailofbits
Find security flaws across your Rust code.
Application security
- 1.6k
agent-owasp-compliance
github
Know which agent security controls are covered or missing.
Agent security
- 1.5k
gke-workload-identity
google
Find why your GKE Pods cannot authenticate.
Cloud authentication
+3 - 1.5k
threat-model-analyst
github
Find security risks in your code and what changed.
Threat modeling
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.