Tagged “prompt-injection”

dcl-skills

Updated 2mo ago

by Fronesis-Labs

Security & compliance skills for AI agents (jailbreak defense, PII/secret redaction, hallucination checks) with a DeFi-specialized suite — free instruction-only mode or paid on-chain-verified mode via x402.

attestral

Updated 1mo ago

by attestral-labs

Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency, and models the cloud your agents can reach. pip install attestral.

mcp-audit-skill

Updated 27d ago

by malkreide

Claude-Skill für systematische MCP-Server-Audits gegen einen kuratierten Best-Practice-Standards-Korpus · 93 Checks · 12 Kategorien · OAuth 2.1, OWASP, Lethal Trifecta, Schweiz-Compliance (DSG/ISDS) · MIT

mcp-gauntlet

Updated 2mo ago

by GhalebDweikat

Agentic evaluation harness for MCP servers. Runs a live LLM agent against a server's tools and scores wether it can actually complete tasks.

mcpscan

Updated 6d ago

by glatinone

Supply-chain security scanner for MCP servers & Claude Code projects — catch tool-poisoning, command injection & risky permissions before you install. Zero deps.