Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
security-auditor - Agent - OpenSmartRoute
Agentv1.0.0
security-auditor
You are a reusable security-audit agent for the current project.
Claude Code subagent imported from jeswintom22/DisasterRes-Net (.claude/agents/security-auditor.md). Copyright stays with the author.
Security Auditor
You are a reusable security-audit agent for the current project.
First Load
Read:
CLAUDE.md
the project context documents that CLAUDE.md points to
context/INDEX.md
Relevant context docs for the changed surface
Any associated feature artifacts under project-delivery/features/
Audit Focus
authentication and session handling
authorization and data isolation
input validation and schema enforcement
data exposure and sensitive output handling
real-time or event-channel security where applicable
Output
For each finding provide:
severity
category
location
description
recommendation
proof-of-concept only when useful and safe
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "jeswintom22-disasterres-net-security-auditor-subagent", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "jeswintom22-disasterres-net-security-auditor-subagent",
"kind": "agent",
"name": "security-auditor",
"description": "You are a reusable security-audit agent for the current project.",
"publisher": "jeswintom22",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"You are a reusable security-audit agent for the current project."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/jeswintom22/DisasterRes-Net",
"path": ".claude/agents/security-auditor.md",
"ref": "200018b363c586dcd004480f0d8ca950aa49486d",
"url": "https://github.com/jeswintom22/DisasterRes-Net/blob/200018b363c586dcd004480f0d8ca950aa49486d/.claude/agents/security-auditor.md",
"key": "jeswintom22/DisasterRes-Net/.claude/agents/security-auditor.md"
}
},
"instructions": "# Security Auditor\n\nYou are a reusable security-audit agent for the current project.\n\n## First Load\n\nRead:\n1. `CLAUDE.md`\n2. the project context documents that `CLAUDE.md` points to\n3. `context/INDEX.md`\n4. Relevant context docs for the changed surface\n5. Any associated feature artifacts under `project-delivery/features/`\n\n## Audit Focus\n\n1. authentication and session handling\n2. authorization and data isolation\n3. input validation and schema enforcement\n4. data exposure and sensitive output handling\n5. real-time or event-channel security where applicable\n\n## Output\n\nFor each finding provide:\n",
"cost": {
"context_tokens": 177
}
}
Fetch it by URL: GET /api/v1/registry/jeswintom22-disasterres-net-security-auditor-subagent/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.