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.
ship-safe - Skill - OpenSmartRoute
Skillv1.0.0
ship-safe
16 parallel security agents scanning 80+ attack classes. Prompt injection, RAG poisoning, API key leaks, supply chain, MCP misconfigurations. Use before production deployment. Don't use for minor code
Imported from paperworkmg-arch/VOLT (app/omni-source/GODMODE/skills/security/ship-safe/SKILL.md). Install upstream with npx skills add paperworkmg-arch/VOLT --skill ship-safe. Copyright stays with the author.
Ship Safe - Full Security Scan
Run comprehensive security scan:
Attack Classes Covered:
Prompt injection vectors
RAG data poisoning
Active API key/secret leaks
Supply chain risks (dependencies)
MCP misconfiguration
Authentication bypasses
Authorization flaws
Data exposure
Injection attacks (SQL, NoSQL, Command)
Cross-site attacks (XSS, CSRF)
Process:
Scan all source code files
Check all configuration files
Audit dependencies (npm audit / pip audit)
Check .env and secrets handling
Verify MCP configurations
Check authentication flows
Report with severity levels
Output:
SCAN COMPLETE
CRITICAL: N issues
HIGH: N issues
MEDIUM: N issues
LOW: N issues
[Detailed report per issue with fix suggestions]
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 - a plan picks it for its slot
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}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
paperworkmg-arch-volt-ship-safe.ocm.jsonjson
{
"ocm": "1",
"id": "paperworkmg-arch-volt-ship-safe",
"kind": "skill",
"name": "ship-safe",
"description": "16 parallel security agents scanning 80+ attack classes. Prompt injection, RAG poisoning, API key leaks, supply chain, MCP misconfigurations. Use before production deployment. Don't use for minor code changes.",
"publisher": "paperworkmg-arch",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"math"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"16 parallel security agents scanning 80+ attack classes. Prompt injection, RAG poisoning, API key leaks, supply chain, MCP misconfigurations. Use before production deployment. Don't use for minor code changes."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/paperworkmg-arch/VOLT",
"path": "app/omni-source/GODMODE/skills/security/ship-safe/SKILL.md",
"ref": "5a41df77fe3ba5e05ebbd8800e2a5e0f85f83569",
"url": "https://github.com/paperworkmg-arch/VOLT/blob/5a41df77fe3ba5e05ebbd8800e2a5e0f85f83569/app/omni-source/GODMODE/skills/security/ship-safe/SKILL.md",
"key": "paperworkmg-arch/VOLT/app/omni-source/GODMODE/skills/security/ship-safe/SKILL.md"
},
"allowed_tools": [
"Bash,",
"Read,",
"Grep,",
"Glob"
]
},
"instructions": "# Ship Safe - Full Security Scan\n\nRun comprehensive security scan:\n\n## Attack Classes Covered:\n- Prompt injection vectors\n- RAG data poisoning\n- Active API key/secret leaks\n- Supply chain risks (dependencies)\n- MCP misconfiguration\n- Authentication bypasses\n- Authorization flaws\n- Data exposure\n- Injection attacks (SQL, NoSQL, Command)\n- Cross-site attacks (XSS, CSRF)\n\n## Process:\n1. Scan all source code files\n2. Check all configuration files\n3. Audit dependencies (npm audit / pip audit)\n4. Check .env and secrets handling\n5. Verify MCP configurations\n6. Check authentication flows\n7. Report wit",
"cost": {
"context_tokens": 191
}
}
Fetch it by URL: GET /api/v1/registry/paperworkmg-arch-volt-ship-safe/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.