Human Agent Trust Exploit Detection

Tencent

Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.

Install

npx skills add Tencent/AI-Infra-Guard --skill human-agent-trust-exploit-detection

npx skills add Tencent/AI-Infra-Guard --skill human-agent-trust-exploit-detection -a claude-code -g

npx skills add Tencent/AI-Infra-Guard --skill human-agent-trust-exploit-detection -a codex -g

gemini skills install https://github.com/Tencent/AI-Infra-Guard.git --path agent-scan/agent_scan/prompt/skills/human-agent-trust-exploit-detection

gh skill install Tencent/AI-Infra-Guard human-agent-trust-exploit-detection

git clone --depth 1 https://github.com/Tencent/AI-Infra-Guard /tmp/Tencent__AI-Infra-Guard
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Tencent__AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/human-agent-trust-exploit-detection ~/.claude/skills/human-agent-trust-exploit-detection   # Claude Code
cp -R /tmp/Tencent__AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/human-agent-trust-exploit-detection ~/.agents/skills/human-agent-trust-exploit-detection   # Codex, Cursor, Gemini CLI, Copilot, OpenCode

Install

Related