🌙 Toggle Dark Mode Home MoltGuard MolTrust Sports MT Shopping MT Travel MT Skills Integrity Dashboard Blog API Docs
EARLY ACCESS

350,000 Skills.
Zero Cryptographic Trust.

MT Skill Verification audits AI agent skills for prompt injection, scope creep, and data exfiltration — then issues W3C Verifiable Credentials signed on Base.

Agent skills are an unaudited attack surface

Blind Loading

Agents load skills from registries with zero verification. Star counts are not trust. A popular skill can still contain hidden prompt injections.

Supply Chain Attacks

One compromised SKILL.md can inject prompts into thousands of agents. There is no signature, no hash, no verification at load time.

No Accountability

Skill authors have no cryptographic identity. No tamper detection exists. If a skill is modified after publication, nobody knows.

Three steps to verified skills

1

Submit a URL

Point to any GitHub repo or HTTPS link containing a SKILL.md file. We fetch the content, normalize it, and compute a canonical SHA-256 hash.

2

8-Point Security Audit

Rule-based scan for prompt injection, data exfiltration, scope violations, capability mismatch, ingestion risk, format validity, and metadata completeness. Score 0–100.

3

VerifiedSkillCredential

W3C Verifiable Credential signed with Ed25519, hash anchored on Base. 90-day validity. Any party can verify independently using the credential hash.

What MT Skill Verification includes

🖧

Canonical SHA-256 Hashing

Deterministic hash spec. Content is normalized before hashing — whitespace, encoding, line endings are standardized. Any party can reproduce and verify the exact same hash.

🛡

8 Security Checks

Prompt injection, data exfiltration, scope violations, capability mismatch, ingestion risk, format validity, metadata completeness, and author identity verification. Each scored individually.

📜

W3C Verifiable Credentials

VerifiedSkillCredential issued with Ed25519 JWS compact serialization. Interoperable W3C standard. Embeds audit score , hash, author DID, and expiry in a portable, machine-readable format.

x402 Micropayments

$5 USDC per credential via the x402 protocol. Payment and issuance in a single HTTP request. Free during Early Access — no signup, no API key required.

👤

Author DID Lookup

Query all credentials by author DID. Build reputation dashboards, track verification history, and discover which skills an author has published and verified over time.

🔍

Tamper-Evident Verification

Any content change = different hash = verification fails. Instant detection. Hash is anchored on Base for immutable proof. No trust assumptions required.

Verify before you load

One API call before loading any skill

Add a single verification step to your agent framework. Before loading any skill from a registry, check its hash against MoltGuard. Get a verified/not-verified response with the full credential.

  • One API call before loading any skill
  • Returns verified/not-verified with full credential
  • Free endpoint, no authentication required
  • Works with any agent framework
API Reference
# Audit a skill
curl "https://api.moltrust.ch/guard/skill/audit?url=https://github.com/org/repo"

# Verify by hash
curl "https://api.moltrust.ch/guard/skill/verify/sha256:ea33b11..."

# Issue a credential
curl -X POST https://api.moltrust.ch/guard/vc/skill/issue \
  -H "Content-Type: application/json" \
  -d '{
    "authorDID": "did:base:0x...",
    "repositoryUrl": "https://github.com/org/repo"
  }'

MT Skill Verification endpoints

Method Endpoint Description Pricing
GET /skill/info Service info and endpoint list Free
GET /skill/schema VerifiedSkillCredential JSON schema Free
GET /skill/audit?url= 8-point security audit for a skill URL Free (5/hr)
POST /vc/skill/issue Issue a VerifiedSkillCredential $5 USDC
GET /skill/verify/:hash Verify a skill by its SHA-256 hash Free
GET /skill/verify/did/:did Look up all credentials by author DID Free

All endpoints are accessible at https://api.moltrust.ch/guard/. Read the full API reference.

Start Verifying Skills Today

All endpoints are free during Early Access. Audit any skill. Issue credentials. Build trust.