Prompt

Prompt from Tencent/AI-Infra-Guard.

Skills in this plugin

14
  1. ▌
    Owasp Asi · tencent-ai-infra-guard
    OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.
    7.5k repo stars
  2. ▌
    Tool Abuse Detection · tencent-ai-infra-guard
    Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
    7.5k repo stars
  3. ▌
    Data Leakage Detection · tencent-ai-infra-guard
    Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
    7.5k repo stars
  4. ▌
    Direct Injection Detection · tencent-ai-infra-guard
    Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.
    7.5k repo stars
  5. ▌
    Hardcoded Secret Detection · tencent-ai-infra-guard
    Detect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.
    7.5k repo stars
  6. ▌
    Memory Poisoning Detection · tencent-ai-infra-guard
    Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.
    7.5k repo stars
  7. ▌
    Web Exfiltration Detection · tencent-ai-infra-guard
    Detect data exfiltration via URL path encoding and chained web_fetch navigation. Covers fake trusted UI injection, letter-level URL path exfiltration, and multi-hop navigation hijacking. Use when the agent has web/URL fetch capability and stores user memory or personal context.
    7.5k repo stars
  8. ▌
    Cascading Failure Detection · tencent-ai-infra-guard
    Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.
    7.5k repo stars
  9. ▌
    Indirect Injection Detection · tencent-ai-infra-guard
    Detect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.
    7.5k repo stars
  10. ▌
    File Path Traversal Detection · tencent-ai-infra-guard
    Detect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.
    7.5k repo stars
  11. ▌
    Authorization Bypass Detection · tencent-ai-infra-guard
    Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.
    7.5k repo stars
  12. ▌
    Human Agent Trust Exploit Detection · tencent-ai-infra-guard
    Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
    7.5k repo stars
  13. ▌
    Inter Agent Comm Security Detection · tencent-ai-infra-guard
    Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.
    7.5k repo stars
  14. ▌
    Unexpected Code Execution Detection · tencent-ai-infra-guard
    Detect command injection, eval/exec usage, remote execution, or arbitrary code loading.
    7.5k repo stars