# Agentic Vulnerabilities

> OWASP Top 10 for Agentic Applications (2026) vulnerability knowledge base for identifying, assessing, and remediating security risks in AI agent systems.

- **Type:** Skill
- **Install:** `agentstack add skill-jasonthedeveloper-owasp-skills-agentic-vulnerabilities`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [JasonTheDeveloper](https://agentstack.voostack.com/s/jasonthedeveloper)
- **Installs:** 0
- **Category:** [Security](https://agentstack.voostack.com/c/security)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [JasonTheDeveloper](https://github.com/JasonTheDeveloper)
- **Source:** https://github.com/JasonTheDeveloper/owasp-skills/tree/main/.github/skills/agentic-vulnerabilities

## Install

```sh
agentstack add skill-jasonthedeveloper-owasp-skills-agentic-vulnerabilities
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Agentic Vulnerabilities — Skill Entry

This `SKILL.md` is the **entrypoint** for the Agentic Vulnerabilities skill.

The skill encodes the **OWASP Top 10 for Agentic Applications (2026)** as structured,
machine-readable references that an agent can query to identify, assess, and remediate
security risks in AI agent systems.

## Normative references (Agentic Top 10)

1. [00 Vulnerability Index](references/00-vulnerability-index.md)
2. [01 Agent Goal Hijack](references/01-agent-goal-hijack.md)
3. [02 Tool Misuse and Exploitation](references/02-tool-misuse-and-exploitation.md)
4. [03 Identity and Privilege Abuse](references/03-identity-and-privilege-abuse.md)
5. [04 Agentic Supply Chain Vulnerabilities](references/04-agentic-supply-chain-vulnerabilities.md)
6. [05 Unexpected Code Execution](references/05-unexpected-code-execution.md)
7. [06 Memory and Context Poisoning](references/06-memory-and-context-poisoning.md)
8. [07 Insecure Inter-Agent Communication](references/07-insecure-inter-agent-communication.md)
9. [08 Cascading Failures](references/08-cascading-failures.md)
10. [09 Human-Agent Trust Exploitation](references/09-human-agent-trust-exploitation.md)
11. [10 Rogue Agents](references/10-rogue-agents.md)

## Skill layout

- `SKILL.md` — this file (skill entrypoint).
- `references/` — the Agentic Top 10 normative documents.
  - `00-vulnerability-index.md` — master index of all vulnerability identifiers, categories, and cross-references.
  - `01` through `10` — one document per vulnerability aligned with OWASP Agentic Security numbering.
- `assets/` — reusable format and constants blocks.
  - `constants/` — vulnerability catalog and category definitions.
    - `constants-agentic-catalog-v1.0.0.md`
  - `formats/` — output contract examples.
    - `format-vulnerability-assessment-v1.0.0.md`
    - `format-remediation-checklist-v1.0.0.md`

## Third-Party Attribution

Copyright © OWASP Foundation.
OWASP® Top 10 for Agentic Applications (2026) content is derived from works by the
OWASP Foundation, licensed under CC BY-SA 4.0
().
Source: 
Modifications: Vulnerability descriptions restructured into agent-consumable reference
documents with added detection and remediation guidance.
OWASP® is a registered trademark of the OWASP Foundation. Use does not imply endorsement.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [JasonTheDeveloper](https://github.com/JasonTheDeveloper)
- **Source:** [JasonTheDeveloper/owasp-skills](https://github.com/JasonTheDeveloper/owasp-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jasonthedeveloper-owasp-skills-agentic-vulnerabilities
- Seller: https://agentstack.voostack.com/s/jasonthedeveloper
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.