Foundry Security Spec
This implements Cisco's Foundry specification for building multi-agent security evaluation systems. It's not a tool you install but a blueprint defining 8 core agent roles (Orchestrator, Planner, Navigator, Detector, Explorer, Validator, Investigator, Publisher) that coordinate to find and validate security issues. The workflow walks you through adopting the constitution's 11 principles via spec-kit, then clarifying integration choices for your environment (which LLM provider, what datastore, deployment target) before generating your customized specification. Good if you're building automated security testing that needs structured coordination between AI agents rather than one monolithic prompt. The detection-to-prevention flywheel is clever: explorers find novel issues that become codified rules for future runs.
- skills.sh installs
- 586
- GitHub stars
- 6
- last updated
- Jul 14, 2026
Install
$ npx -y skills add aradotso/security-skills --skill foundry-security-spec --agent claude-codeInstalls into .claude/skills of the current project.
Files
Foundry Security Spec
Skill by ara.so — Security Skills collection.
Foundry is an open specification from Cisco for building agentic AI security evaluation systems. It defines a multi-agent architecture with 8 core roles and 5 extension roles that coordinate to discover, validate, and report security findings. This is NOT a tool to install—it's a blueprint for building your own security evaluation system.
Core Concepts
Foundry provides:
- Architecture: 8 core agent roles (Orchestrator, Planner, Navigator, Detector, Explorer, Validator, Investigator, Publisher)
- Finding Lifecycle: States, verdicts, evidence gates, fingerprinting
- Coordination Model: Atomic claims, heartbeat liveness, auto-blocking
- Governance: Sandboxing, budgets, yield-gated auto-stop, coverage gates
- Detection-to-Prevention Flywheel: Rules catch known issues, explorers find new ones, gaps become new rules
Works with CodeGuard rule format for portable detection rules that transfer between evaluation and prevention.
Repository Structure
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/aradotso/security-skills
- Categories
- Security, Web3 & Blockchain
- First seen
- Jul 14, 2026
More from aradotso/security-skills
All 58- Anthropic Cybersecurity Skills1.3K
- Pentest Ai Agents1.1K
- Pentest Agents Bug Bounty Framework1K
- Openosint Ai Osint Framework992
- Vibe Security Skill976
- Openclaw Security Hardening971
- Malware Detection Awareness960
- Slowmist Agent Security Framework955
- Autopentestx Automated Pentesting950
- Avast Premium Security Analysis947
- Malware Warning Avast Keygen945
- Palisade Security Nexus Bitdefender937
- Malware Warning Avast Piracy934
- Avast Security Awareness933
- Report Malicious Repository927
- Unisecurityguard Academic Whistleblower Archive925
- Wxmini Security Audit919
- Avast Premium Security Detection918
- Security Awareness Malicious Repository Detection909
- Avast Premium Security Malware Analysis905
- Avast Premium Security Awareness898
- Avast Security Analysis897
- Openclaw Security Watchdog856
- Security Threat Awareness852
Recommended
More Security
recipe-triage-security-alertsgoogleworkspace/cliList and review Google Workspace security alerts from Alert Center.583skills.sh installs
security-webshellseyadkelleh/awesome-skills-securityWeb shell samples for detection and analysis: PHP, ASP, ASPX, JSP, Python, Perl shells. Use for security research and detection system testing.580skills.sh installssecurity-usernameseyadkelleh/awesome-skills-securityTop username lists for enumeration: common usernames, default credentials, names. Curated essentials for authorized testing.577skills.sh installs
security-audit-loggingaj-geddes/useful-ai-promptsImplement comprehensive security audit logging for compliance, forensics, and SIEM integration. Use when building audit trails, compliance logging, or security 568skills.sh installs
longbridge-security-listlongbridge/skillsUS overnight-eligible securities directory and HK broker participant directory via Longbridge Securities. `security-list` covers the US overnight-trading catalo524skills.sh installs
skill-security-auditsmartchainark/skill-security-auditDetect malicious patterns in AI Agent skills — 13 detectors for backdoors, credential theft, data exfiltration, and supply-chain attacks. Based on SlowMist's Cl519skills.sh installs