owasp-asi
starsforks
How to install owasp-asi?
tencent/ai-infra-guard/owasp-asi
$npx -y skills add Tencent/AI-Infra-Guard --skill owasp-asiOWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.
SKILL.md
| 1 | # OWASP ASI Classification Framework |
| 2 | |
| 3 | **OWASP Top 10 for Agentic Applications 2026** - Standardized risk classification for AI agent security. |
| 4 | |
| 5 | ## Risk Categories |
| 6 | |
| 7 | | ID | Risk Type | Key Indicators | |
| 8 | |:---|:----------|:---------------| |
| 9 | | **ASI01** | Agent Goal Hijack | Prompt injection, instruction override, goal manipulation | |
| 10 | | **ASI02** | Tool Misuse & Exploitation | Unauthorized tool calls, parameter tampering, unvalidated inputs | |
| 11 | | **ASI03** | Identity & Privilege Abuse | Auth bypass, permission escalation, missing authorization | |
| 12 | | **ASI04** | Agentic Supply Chain | Malicious dependencies, compromised tools, package poisoning | |
| 13 | | **ASI05** | Unexpected Code Execution | RCE, command injection, code evaluation | |
| 14 | | **ASI06** | Memory & Context Poisoning | Data leakage, context manipulation, memory corruption | |
| 15 | | **ASI07** | Insecure Inter-Agent Comm | Unencrypted channels, data exposure between agents | |
| 16 | | **ASI08** | Cascading Failures | Error propagation, chain reaction vulnerabilities | |
| 17 | | **ASI09** | Human-Agent Trust Exploit | Social engineering, deceptive responses | |
| 18 | | **ASI10** | Rogue Agents | Malicious agent behavior, unauthorized actions | |
| 19 | |
| 20 | ## Detection Source → ASI Mapping |
| 21 | |
| 22 | | Detection Source | Type | Primary ASI | Secondary ASI | |
| 23 | |:-----------------|:-----|:------------|:--------------| |
| 24 | | `data-leakage-detection` | Skill | ASI06, ASI07 | ASI01, ASI03 | |
| 25 | | `tool-abuse-detection` | Skill | ASI02, ASI05, ASI07 | ASI03 | |
| 26 | | `indirect-injection-detection` | Skill | ASI01 | ASI06 | |
| 27 | | `authorization-bypass-detection` | Skill | ASI03 | ASI09 | |
| 28 | | Prompt Injection tests | Dialogue | ASI01, ASI06 | ASI09 | |
| 29 | | Code Audit | Agent | ASI04, ASI05 | ASI10 | |
| 30 | |
| 31 | ## Finding → ASI Mapping |
| 32 | |
| 33 | | Finding Type | ASI Category | Rationale | |
| 34 | |:-------------|:-------------|:----------| |
| 35 | | API keys, tokens | ASI06 | Context contains sensitive data | |
| 36 | | System prompts | ASI01 | Enables goal hijacking | |
| 37 | | Credentials | ASI03 | Identity abuse risk | |
| 38 | | Internal configs | ASI04 | Supply chain exposure | |
| 39 | | PII exposure | ASI07 | Inter-agent data leak | |
| 40 | | Command injection | ASI05 | Unexpected code execution | |
| 41 | | Unauthorized tool calls | ASI02 | Tool misuse | |
| 42 | |
| 43 | ## Severity Classification |
| 44 | |
| 45 | ### Critical 🚨 |
| 46 | - Complete private keys exposed |
| 47 | - Production credentials with unrestricted access |
| 48 | - Remote code execution confirmed |
| 49 | - Full agent takeover possible |
| 50 | |
| 51 | **Action**: Immediate remediation (within 24 hours) |
| 52 | |
| 53 | ### High ⚠️ |
| 54 | - API keys with limited scope |
| 55 | - Authentication tokens |
| 56 | - System prompt disclosure |
| 57 | - Partial credential exposure |
| 58 | |
| 59 | **Action**: Urgent remediation (within 1 week) |
| 60 | |
| 61 | ### Medium 💡 |
| 62 | - Configuration details |
| 63 | - Internal endpoints |
| 64 | - Metadata leakage |
| 65 | - Conditional exploitation paths |
| 66 | |
| 67 | **Action**: Address within 2-4 weeks |
| 68 | |
| 69 | ### Low ℹ️ |
| 70 | - Generic system information |
| 71 | - Non-sensitive configurations |
| 72 | - Indirect hints |
| 73 | |
| 74 | **Action**: Review as time permits |
| 75 | |
| 76 | ## Usage |
| 77 | |
| 78 | Load this skill when performing OWASP ASI classification: |
| 79 | |
| 80 | ```python |
| 81 | load_skill(name="owasp-asi") |
| 82 | ``` |
| 83 | |
| 84 | Then apply the mapping rules to classify findings. |
People who liked this also viewed
6 picksType
- entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API perSkillsJul 2026
- azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: SkillsJul 2026
- azure-rbacOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026
- better-auth-best-practicesAgent skill from better-auth/skillsSkillsJul 2026
- firebase-security-rules-auditorA skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are extremely secure and robust.SkillsJul 2026
- audit-websiteAudit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-opSkillsJul 2026
