aktoakto-api-security/akto
Provides security testing and guardrail validation for LLM applications, AI Agents and MCP toolchains,…
No ratings yet
Rate this skill
Stars1.5k
Forks293
Watchers1.5k
Open Issues356
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/akto-api-security/akto.git
OverviewOverview
Key Features
Provides security testing and guardrail validation for LLM applications, AI Agents and MCP toolchains, helping uncover prompt injection, jailbreak and tool-abuse risks before AI features go live. Key capabilities include: 1. Prompt injection and jailbreak testing: built-in attack cases against LLMs are executed on the target model or application, producing reproducible vulnerability findings; 2. OWASP risk checklist coverage: test items are organized around OWASP LLM Top 10, Agentic Top 10 and MCP Top 10 to verify the application's exposure to each risk; 3. Agent and MCP toolchain inspection: security probing of Agent tool invocations and MCP service endpoints to identify privilege-escalation calls and sensitive data leakage paths; 4. Guardrail validation: bypass testing against deployed input/output guardrails to confirm whether protection rules actually take effect; 5. Red team execution and result retention: attack cases are run in batches from a red-team perspective with test records kept for retesting and fix verification; 6. Localized deployment: Docker-based startup steps for macOS and Linux (including creating code and MongoDB data directories and starting services across multiple terminals) allow the testing platform to run independently on a local machine or intranet.
Use Cases
Target Roles
Network & System Security Engineer, AI / Algorithm Engineer, Test / QA Engineer, Backend Developer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1647 |
|---|---|
| Data source | GitHub |
| Repository | akto-api-security/akto |
| Category | Network & System Security / AI Security Testing & Guardrails |
| Primary language | Java |
| License | MIT License |
| Default branch | master |
| GitHub repository ID | 595526110 |
| Node ID | R_kgDOI38B3g |
| Rank | #532 (position within the source ranking) |
| Site-wide popularity rank | #619 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now1,528
- Previous point · 09-29 1,521
- vs previous point +7
- 2 data points 12 days
- Now293
- Previous point · 09-29 294
- vs previous point -1
- 2 data points 12 days
TimelineTimeline
Repository created2023-01-31 09:07:072023-01-31
Data last updated2026-10-26 11:59:4723 days ago
Last commit2026-10-10 20:11:431 months ago
CommitLatest commit
Committed by Ark2307. Update Category: Security Hardening & Vulnerability Fixes. Commit details: Merge pull request #6637 from akto-api-security/feat/paginated-api-collections. This update patches security issues that could be exploited; upgrading is recommended.