---
title: "owasp-asi02-tool-misuse"
description: "Constrain what an agent's legitimate tools can be made to do. Grant least agency per task, validate tool parameters at the runtime boundary, authorise every invocation rather than only the first, and distrust tool metada"
canonical: https://agentpluginsdirectory.com/plugins/owasp-asi02-tool-misuse
last-updated: 2026-10-21
---

# owasp-asi02-tool-misuse
Constrain what an agent's legitimate tools can be made to do. Grant least agency per task, validate tool parameters at the runtime boundary, authorise every invocation rather than only the first, and distrust tool metadata from unverified registries. Use when defining tool schemas, wiring an MCP server, granting shell or cloud-CLI access, or reviewing a tool-calling loop. Do NOT use for the credentials the tool authenticates with, that is `owasp-asi03-identity-privilege-abuse`.
- Slug: owasp-asi02-tool-misuse
- Publisher: chock-core
- Repository: https://github.com/open-coder-ai/chock-catalog
- Manifest: agentic-security/owasp-asi02-tool-misuse/plugin.json
- Version: 0.0.2
- License: Apache-2.0
- Category (editorial): security
- Skills: 1 (owasp-asi02-tool-misuse)
- MCP servers: 0
- Stars: 3
- Repository created: 2026-08-17
- Repository last pushed: 2026-10-21
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/owasp-asi02-tool-misuse
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- owasp-asi02-tool-misuse: Constrain what an agent's legitimate tools can be made to do. Grant least agency per task, validate tool parameters at the runtime boundary, authorise every invocation rather than only the first, and distrust tool metadata from unverified registries. Use when defining tool schemas, wiring an MCP se…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.