27 results
mcp
dagoSte/reverseai
Static reverse engineering of untrusted files with verifiab…
Warn
mcp
alphaparkinc/genpark-agent-prompt-guard-injection-sanitizer-skill
Strict heuristic and regex-based prompt injection and untru…
Warn
mcp
Alpha-Park/genpark-agent-prompt-guard-injection-sanitizer-skill
Strict heuristic and regex-based prompt injection and untru…
Warn
mcp
Alpha-Park/genpark-prompt-injection-dual-llm-canary-verifier-skill
Verifies untrusted user prompt payloads against adversarial…
Warn
mcp
alphaparkinc/genpark-agentic-prompt-injection-jailbreak-firewall-sentinel-skill
Zero-Trust Agentic Indirect Prompt Injection & Jailbreak Fi…
Warn
mcp
Alpha-Park/genpark-agentic-prompt-injection-jailbreak-firewall-sentinel-skill
Zero-Trust Agentic Indirect Prompt Injection & Jailbreak Fi…
Warn
mcp
plimsollmark/plimsoll
A sandbox service for running untrusted, agent-authored cod…
Warn
mcp
macmaia/catraca
Provenance-aware authorisation for LLM agent tool calls. De…
Warn
agent
kgpp34/KumaBox
A daemonless microVM sandbox runtime for agents, automation…
Fail
agent
binuka200/package-doctor
Scan Python dependencies for exploited CVEs and abandoned p…
Warn
mcp
hermes-labs-ai/little-canary
Detects prompt injection by its effect on a sacrificial can…
Pass
mcp
chamuka-inc/vmette
A hardware-isolated microVM sandbox for running untrusted l…
Warn