CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kleros-curate

Interact with Kleros Curate registries across Ethereum Mainnet, Gnosis Chain, and Sepolia. Use when the user mentions Curate, Light Curate/LightGeneralizedTCR/LGTCR, Stake Curate/PermanentGTCR/PGTCR, Scout, token-curated registry/TCR, token lists, address/CDN tags, Goldsky, MetaEvidence, Verify Your List, or Curate calls such as addItem, removeItem, challengeItem, challengeRequest, and fundAppeal. Covers registry discovery and queries; policy/schema inspection; submissions, removals, challenges, evidence, appeals, rewards, execution; factory deployment; and frontend verification on all three networks. Also trigger for registry/list operations paired with Kleros, arbitrator, dispute, juror, or PNK context, and whenever the user names or tests kleros-curate. Do NOT use for non-Kleros registries or generic IPFS uploads without Curate context; route standalone uploads to kleros-ipfs-upload.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security
Medium

W009: Direct money access capability detected (payment gateways, crypto, banking).

What this means

The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.

Why it was flagged

Direct financial operations are documented: the submitter "locks a submission deposit" (SKILL.md:14-15), challengers "lock a challenge deposit" (SKILL.md:20-21), and the workflows instruct the agent to compute exact `msg.value` and "send the addItem transaction" (SKILL.md:137-138) or "send the challenge or removeItem transaction" (SKILL.md:143-144). Fund-an-appeal is also an action (SKILL.md:111). Depositing and paying into contracts is a transfer of value, so these are direct operations, not indirect ones. Winners capturing bounties (SKILL.md:22-23) also make the flow financial. The skill is in scope, and the exclusions for development or information do not apply, since the agent itself performs these transactions. Control: no independent authentication or authorization for these payment routes is documented. The only safeguards are agent-followed rules such as "Never guess" amounts and "Always read live values" (SKILL.md:35-37, 55-57). Local wallet signing does not count as an access control. Nothing in the file describes a service or execution-layer check that gates the deposit, challenge, or appeal-funding transactions. Because the direct operations lack a qualifying control, severity is High.

Report incorrect finding
Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

Verify-your-list's required duplicate/compliance check scans NewItem logs on the verification LightGeneralizedTCR from its deployment block and fetches every item JSON, and anyone can permissionlessly addItem into that registry, so outsider-authored free text reaches the agent without it selecting a specific item.

Low

W012: Unverifiable external dependency detected (runtime URL that controls agent).

What this means

The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.

Why it was flagged

The decisive boundary is that the hardcoded Goldsky subgraph endpoints supply registry configuration (metaEvidenceURI, arbitratorExtraData, deposit parameters) that the skill adopts to drive submission workflows, and their publisher is only plausibly Kleros-operated rather than established as first-party, so the tier is medium for an unofficial-but-reputable hosted indexer.

Repository

internet-court/internet-court-skill

Path

vendored/kleros/kleros-curate/SKILL.md

Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.