# ai-infra-guard: a set by tencent

The tencent/ai-infra-guard repository on GitHub: 17 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

17 cards

- HTML: https://affpapa.org/en/nevibecode/by/tencent/ai-infra-guard
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [web-exfiltration-detection](https://affpapa.org/en/nevibecode/skills/web-exfiltration-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The web-exfiltration-detection skill tests whether an agent can be coaxed into exposing memory through a chain of web navigation.
- [tool-abuse-detection](https://affpapa.org/en/nevibecode/skills/tool-abuse-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — tool-abuse-detection runs dialogue probes against an agent to catch command execution, out-of-scope file reads and SSRF.
- [owasp-asi](https://affpapa.org/en/nevibecode/skills/owasp-asi.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — owasp-asi maps AI agent security findings to the OWASP Top 10 for Agentic Applications 2026 standard and defines remediation deadlines.
- [memory-rag-poisoning-detection](https://affpapa.org/en/nevibecode/skills/memory-rag-poisoning-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The memory-rag-poisoning-detection skill tests whether an agent stores hostile instructions in memory or a knowledge base and follows them in later conversations.
- [memory-poisoning-detection](https://affpapa.org/en/nevibecode/skills/memory-poisoning-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The memory-poisoning-detection skill checks whether an agent stores a hostile instruction in long-term memory and follows it in later tasks.
- [inter-agent-comm-security-detection](https://affpapa.org/en/nevibecode/skills/inter-agent-comm-security-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — inter-agent-comm-security-detection probes inter-agent communications for data exposure, spoofing, and privilege escalation.
- [human-agent-trust-exploit-detection](https://affpapa.org/en/nevibecode/skills/human-agent-trust-exploit-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The human-agent-trust-exploit-detection skill checks whether an agent solicits secrets, gives misleading safety claims, or pushes users toward risky actions.
- [hardcoded-secret-detection](https://affpapa.org/en/nevibecode/skills/hardcoded-secret-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The hardcoded-secret-detection skill has the agent scan the source, configs and IaC it can reach for keys, tokens and passwords sitting in plain text.
- [file-path-traversal-detection](https://affpapa.org/en/nevibecode/skills/file-path-traversal-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — file-path-traversal-detection is a Claude Code skill that tests whether an AI agent writes outside its workspace when saving files or extracting archives.
- [direct-injection-detection](https://affpapa.org/en/nevibecode/skills/direct-injection-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — direct-injection-detection is a Claude Code skill that tests whether a user message can override system or developer instructions.
- [data-leakage-detection](https://affpapa.org/en/nevibecode/skills/data-leakage-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — data-leakage-detection — a skill that runs escalating dialogue probes against an agent to surface leaked system prompts, credentials, PII and internal config.
- [cascading-failure-detection](https://affpapa.org/en/nevibecode/skills/cascading-failure-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — cascading-failure-detection identifies cascading failure risks in multi-step agent workflows.
- [authorization-bypass-detection](https://affpapa.org/en/nevibecode/skills/authorization-bypass-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The authorization-bypass-detection skill probes an agent for access to other users’ data and actions beyond the caller’s permissions.
- [agentic-supply-chain-detection](https://affpapa.org/en/nevibecode/skills/agentic-supply-chain-detection.md) — skill · Tencent · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The agentic-supply-chain-detection skill probes whether your agent pulls plugins, models or updates from untrusted sources.
- [edgeone skill scanner](https://affpapa.org/en/nevibecode/skills/edgeone-skill-scanner.md) — skill · Tencent Zhuque Lab · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — edgeone skill scanner runs local static analysis on agent skills to detect backdoors, credential theft, and permission abuse before you run them.
- [edgeone-clawscan](https://affpapa.org/en/nevibecode/skills/edgeone-clawscan.md) — skill · aigsec/Tencent Zhuque Lab · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — edgeone-clawscan is a Claude Code skill that checks OpenClaw security and reviews installed skills.
- [aig-scanner](https://affpapa.org/en/nevibecode/skills/aig-scanner.md) — skill · aigsec/Tencent Zhuque Lab · Claude Code, Codex, Cursor +5 · ★ 7607 repo stars — The aig-scanner skill files and tracks AI security scans on a Tencent AI-Infra-Guard server, covering services, MCP projects, agents and jailbreak checks.

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
