Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add emiliaprotocol/emilia-protocol --skill emilia-trust-verificationgit clone --depth 1 https://github.com/emiliaprotocol/emilia-protocolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emiliaprotocol/emilia-protocol/emilia-trust-verification)<a href="https://agentmods.dev/skills/emiliaprotocol/emilia-protocol/emilia-trust-verification"><img src="https://agentmods.dev/badge/skills/emiliaprotocol/emilia-protocol/emilia-trust-verification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emiliaprotocol/emilia-protocol/emilia-trust-verification"><img src="https://agentmods.dev/badge/skills/emiliaprotocol/emilia-protocol/emilia-trust-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01115 |
| Opus 5 | $0.00047 | $0.00558 |
| Sonnet 5 | $0.00019 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
EMILIA Trust Verification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EMILIA Trust Verification
EMILIA Protocol makes a high-risk AI-agent action carry a device-key signoff
plus a receipt anyone can verify offline. This skill guides you to verify
those artifacts using the public EMILIA MCP connector. It requires the
connector to be enabled (server URL
https://www.emiliaprotocol.ai/api/mcp/mcp, read-only, no auth).
When to use this skill
Engage when the user:
- Pastes a JSON object with
"@version": "EP-RECEIPT-v1"(a trust receipt), or asks "is this receipt real / altered / valid?" - Pastes an object with a
context+webauthnblock (a device signoff), or asks whether the WebAuthn/passkey ceremony and exact-action binding verify.
If the user mentions a receipt or signoff but hasn't pasted it, ask them for the JSON (they can copy a real example from https://www.emiliaprotocol.ai/verify).
The two public tools
| Tool | Use it to |
|---|---|
ep_verify_receipt |
Verify an EP-RECEIPT-v1 receipt — Ed25519 signature over canonical JSON + optional Merkle anchor. |
ep_verify_signoff |
Verify a Class-A device signoff — a WebAuthn (ECDSA P-256) assertion bound to the exact action. |
Each verify tool accepts the JSON object directly; the public key can be passed
explicitly or, for self-contained evidence packets, is read from an embedded
issuer_public_key / approver_public_key field.
How to interpret results
Receipt — { valid, checks: { version, signature, anchor } }:
valid: true→ the receipt was signed by its issuer and has not been altered. State this plainly; the user can re-verify it themselves, offline, forever.valid: falsewithsignature: false→ the receipt does not match its signature — it was tampered with, or the wrong key was used. Do not treat a failed receipt as trustworthy. Call out which check failed.anchor: false→ the Merkle inclusion proof does not reconstruct the claimed root (the anchor was altered).
Signoff — six checks. All must be true for valid: true:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 94 lines · 94 tokens per session scan A 391dd7ac35d9
EMILIA Trust Verification is a skill published in the GitHub repository emiliaprotocol/emilia-protocol (649 stars, last pushed 2d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,115 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-inspector
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
api-caller
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
calculator
Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.
task-list
Required for 4+ step requests; add tasks at start and update status after each step.
text-analyzer
Analyze text content and produce statistics including word count, line count, character count, most frequent words, and readability metrics. Works on any plain text input provided inline or from a file path.