Skip to content
Agentmart
Submit a tool

ash-security

Change or review Ash authorization, trusted scopes and field exposure.

Skill by regents-ai

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/regents-ai-ash-security

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Change or review Ash authorization, trusted scopes and field exposure.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ash-security

What's inside

Skill name
ash-security
Description
Change or review Ash authorization, trusted scopes and field exposure.
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Files (5)

  • SKILL.md
  • openai.yaml · agents/
  • component-session-check.md · references/
  • operator-actions.md · references/
  • threat-cases.md · references/

SKILL.md (first lines)

# Ash Security

Follow the operation's actor, tenant and accepted inputs from its actual entry point
to the resource action. Reuse the application's trusted scope representation.
A supplied tenant ID is not proof of membership; a browser state is not authorization.

[Threat cases](references/threat-cases.md) covers cross-tenant references, privilege
changes, nested data, field exposure and background execution.
[Operator actions](references/operator-actions.md) covers who an operator is, staff
pages, release commands that change live data, the record they leave and development
tools.
[Component session check](references/component-session-check.md) covers LiveComponents,
whose events skip the page's session re-check.

Explicit Ash options can replace scope-derived values: `actor: nil` may erase the
scope's actor. Inspect wrapper defaults and keyword merges. In callbacks, propagate
the supplied context using the installed API rather than stale request state.

Unauthorized reads can filter records or return not-found; test non-disclosure under
the actual policy contract instead of requiring Forbidden everywhere. For writes,
prove that a rejected operation did not change protected state.

For Regent Privy/session work, consult [Privy reconciliation](../ash-stack/references/privy-reconciliation.md).
This review guidance does not create another workflow stage or approval boundary.

From regents-ai/ash-template, MIT.

More from regents-ai/ash-template

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from regents-ai

Cite this page

ash-security skill. Agent Mart. https://agentmart.dev/skills/regents-ai-ash-security (last updated 2026-10-24)