xproof-8f9e81 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited xproof-8f9e81 (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill certifies agent outputs on the MultiversX blockchain using xProof. Every certification creates an immutable, publicly verifiable proof-of-existence — anchored on-chain, not stored by xProof.
Use this skill whenever the agent produces an output that matters: a research report, a data analysis, a recommendation, a decision. The blockchain proof means anyone can verify what was produced, when it was produced, and who produced it — without trusting the agent.
proof_id and transaction_hash are returnedhttps://xproof.app/proof/<proof_id>Get a free API key (10 certifications included):
curl -s -X POST https://xproof.app/api/agent/register \
-H "Content-Type: application/json" \
-d '{"agent_name": "my-deerflow-agent"}' | jq .Save the api_key from the response. Set it as an environment variable:
export XPROOF_API_KEY="pm_..."# 1. Hash the content
CONTENT="Q3 revenue analysis: $4.2M, up 15% YoY"
HASH=$(echo -n "$CONTENT" | sha256sum | cut -d' ' -f1)
# 2. Certify on-chain
curl -s -X POST https://xproof.app/api/proof \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $XPROOF_API_KEY" \
-d "{
\"file_hash\": \"$HASH\",
\"file_name\": \"q3-analysis.json\",
\"author\": \"deerflow-agent\",
\"metadata\": {
\"who\": \"deerflow-agent\",
\"what\": \"$HASH\",
\"when\": \"$(date -u +%Y-%m-%dT%H:%M:%S.000Z)\",
\"why\": \"Quarterly earnings certification\",
\"framework\": \"deerflow\"
}
}" | jq .Response:
{
"id": "proof-abc123",
"fileHash": "a1b2c3...",
"transactionHash": "0xdeadbeef...",
"verifyUrl": "https://xproof.app/proof/proof-abc123",
"explorerUrl": "https://explorer.multiversx.com/transactions/0xdeadbeef..."
}pip install xprooffrom xproof.integrations.deerflow import XProofDeerFlowSkill
skill = XProofDeerFlowSkill(api_key="pm_...")
# Plain text
result = skill._run("My research findings")
# With metadata
result = skill._run('{"content": "Q3 analysis", "why": "Quarterly review"}')from xproof.integrations.langchain import XProofCallbackHandler
handler = XProofCallbackHandler(api_key="pm_...")
# Pass to your LangGraph/LangChain config — all LLM calls and tool invocations auto-certifyCertify up to 50 outputs in a single API call:
curl -s -X POST https://xproof.app/api/batch \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $XPROOF_API_KEY" \
-d '{
"files": [
{"file_hash": "abc123...", "file_name": "report-1.json"},
{"file_hash": "def456...", "file_name": "report-2.json"}
]
}' | jq .Anyone can verify a proof — no API key needed:
curl -s https://xproof.app/api/proof/<proof_id> | jq .Or visit: https://xproof.app/proof/<proof_id>
Every certification answers four questions:
| Question | Field | Description |
|---|---|---|
| WHO | who | Which agent produced the output |
| WHAT | what | SHA-256 hash of the content (the content itself stays private) |
| WHEN | when | Blockchain timestamp — written by the chain, not the agent |
| WHY | why | Context: why was this output produced |
/api/agent/register. Purchase more at $0.05/cert.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.