Security & Testing Agent Skills for HTTP / API

EU AI Act compliance gatekeeper. Use when the user is developing AI systems, writing AI code, integrating APIs (OpenAI, Anthropic)…

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade…

Use when testing an LLM-backed feature, prompt, tool loop or multi-step agent, where the same input can produce different outputs and a…

Evaluates and selects Threat Intelligence Platform (TIP) products based

Build evaluation frameworks for agent systems.

Implement security best practices for Evernote integrations.

Enforces rigorous validation protocols by requiring real-time command outputs and evidence before any task is marked as complete.

Evidence-capture and PoC-redaction discipline for bug-bounty submissions: cookie redaction protocol (which fields to mask, Preview…

Deep EVM bytecode analysis and decompilation capabilities for smart contract security, gas optimization, and reverse engineering.

Help users simulate Ethereum transactions, preview state changes, decode call trees, extract token transfers, decode revert reasons, debug…

Secure Exa API keys, implement content moderation, and manage domain

Executes authorized attack simulations against Active Directory environments

Executes authorized phishing simulation campaigns to assess an organization''s

Build the foundational red team engagement plan - scope definition, Rules

Run a stealthy, MITRE ATT&CK-mapped adversary emulation against an organization''s

Guides developers through Exemplar Relay — coding-agent governance for Claude Code, Cursor, Codex, and OpenCode.

BloodHound is a graph-based Active Directory reconnaissance tool that

Tests API parameters, headers, and request bodies for injection flaws — SQL injection, NoSQL injection, OS command injection, LDAP…

Tests APIs for Broken Function Level Authorization (OWASP API5:2023) by identifying admin and privileged endpoints, then reaching them…

Discovers and exploits broken link hijacking by spidering a site (Burp Suite Spider, Scrapy, curl scraping), extracting referenced…