Slowmist Agent Security Framework
If you're building agents that install third-party skills, pull from GitHub repos, or process user-shared URLs, this gives you a structured paranoia framework. It walks through six review types (skills, repos, URLs, on-chain addresses, products, social shares) with red flag databases for obfuscation, credential theft, and prompt injection patterns. The risk rating system is clear: green means inform and proceed, red means block until human approval, reject means refuse outright. Built by SlowMist, so the threat modeling leans heavily on adversarial scenarios like typosquatting dependencies and base64-encoded exfiltration endpoints. Treat it as a checklist for agents operating in environments where every external input could be hostile.
- skills.sh installs
- 955
- GitHub stars
- 6
- last updated
- Jul 14, 2026
Install
$ npx -y skills add aradotso/security-skills --skill slowmist-agent-security-framework --agent claude-codeInstalls into .claude/skills of the current project.
Files
SlowMist Agent Security Framework
Skill by ara.so — Security Skills collection.
A structured security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.
What This Framework Does
SlowMist Agent Security provides:
- Skill/MCP Installation Review — Detect malicious patterns before installation
- GitHub Repository Auditing — Security assessment of codebases
- URL/Document Analysis — Prompt injection and social engineering detection
- On-Chain Address Review — AML risk assessment and transaction analysis
- Product/Service Evaluation — Architecture and permission analysis
- Social Share Review — Validate tools recommended in conversations
Installation
Clone the framework into your agent's workspace:
# For OpenClaw
cd ~/.openclaw/workspace/skills
git clone https://github.com/slowmist/slowmist-agent-security.git
# For other agent systems
cd /path/to/agent/skills
git clone https://github.com/slowmist/slowmist-agent-security.git
Once installed, the agent automatically references this framework when encountering untrusted inputs.
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, AI & Agent Building
- First seen
- Jul 14, 2026
More from aradotso/security-skills
All 58- 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
- Malware Analysis DragonflyTomb Avast851
- Avast Premium Security Malware Detection837
- Mcp Security Hub827
- Identify Malicious Repository823
- Bitdefender Total Security Malware Analysis817
- Malware Warning Bitdefender Crack817
- Bitdefender Total Security Awareness799
- Malware Detection And Removal796
Recommended
More Security
palisade-security-nexus-bitdefenderaradotso/security-skillspalisade security nexus bitdefender937skills.sh installs
security-compliancedavila7/claude-code-templatesGuides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPA848skills.sh installsnpm-security-best-practicesaradotso/security-skillsnpm security best practices770skills.sh installs