NeVibeCode · repository · 17 items
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.
About the repository
- GitHub
- tencent/ai-infra-guard
- Stars
- ★ 7,607
- Licenses
- Apache-2.0, MIT
- Source updated
- 2026-10-22
- In the catalog since
- 2026-10-26
web-exfiltration-detection skill The web-exfiltration-detection skill tests whether an agent can be coaxed into exposing memory through a chain of web navigation. Use it when the agent fetches pages and retains personal context.
CX Codex +1
★ 7,607repo stars
tool-abuse-detection skill tool-abuse-detection runs dialogue probes against an agent to catch command execution, out-of-scope file reads and SSRF. Useful when the agent holds file, code or network tools.
CX Codex +1
★ 7,607repo stars
owasp-asi skill owasp-asi maps AI agent security findings to the OWASP Top 10 for Agentic Applications 2026 standard and defines remediation deadlines.
CX Codex +1
★ 7,607repo stars
memory-rag-poisoning-detection skill 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.
CX Codex +1
★ 7,607repo stars
memory-poisoning-detection skill The memory-poisoning-detection skill checks whether an agent stores a hostile instruction in long-term memory and follows it in later tasks.
CX Codex +1
★ 7,607repo stars
inter-agent-comm-security-detection skill inter-agent-comm-security-detection probes inter-agent communications for data exposure, spoofing, and privilege escalation. Useful when agents share context or route messages.
CX Codex +1
★ 7,607repo stars
human-agent-trust-exploit-detection skill The human-agent-trust-exploit-detection skill checks whether an agent solicits secrets, gives misleading safety claims, or pushes users toward risky actions. Use it for dialogue-based security checks.
CX Codex +1
★ 7,607repo stars
hardcoded-secret-detection skill 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.
CX Codex +1
★ 7,607repo stars
file-path-traversal-detection skill 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.
CX Codex +1
★ 7,607repo stars
direct-injection-detection skill direct-injection-detection is a Claude Code skill that tests whether a user message can override system or developer instructions. It checks an AI agent for direct prompt injection.
CX Codex +1
★ 7,607repo stars
data-leakage-detection skill data-leakage-detection — a skill that runs escalating dialogue probes against an agent to surface leaked system prompts, credentials, PII and internal config.
CX Codex +1
★ 7,607repo stars
cascading-failure-detection skill cascading-failure-detection identifies cascading failure risks in multi-step agent workflows. It tests dependency outages and unbounded retry loops.
CX Codex +1
★ 7,607repo stars
authorization-bypass-detection skill The authorization-bypass-detection skill probes an agent for access to other users’ data and actions beyond the caller’s permissions. Use it when an agent handles roles, user data, or admin functions.
CX Codex +1
★ 7,607repo stars
agentic-supply-chain-detection skill The agentic-supply-chain-detection skill probes whether your agent pulls plugins, models or updates from untrusted sources. Useful when a project leans on third-party dependencies.
CX Codex +1
★ 7,607repo stars
edgeone skill scanner skill edgeone skill scanner runs local static analysis on agent skills to detect backdoors, credential theft, and permission abuse before you run them.
CX Codex +1
★ 7,607repo stars
edgeone-clawscan skill edgeone-clawscan is a Claude Code skill that checks OpenClaw security and reviews installed skills. Run it to audit an environment or assess a skill before installation.
CX Codex +1
★ 7,607repo stars
aig-scanner skill 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.
CX Codex +1
★ 7,607repo stars