Caveat verdict

opensea

opensea-marketplace

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Router skill dispatching to well-documented OpenSea sub-skills; no operational code, no suspicious behavior, just a routing table pointing to official OpenSea GitHub repos.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
80
maintenance

Findings (7)

Pattern match critical

Possible hardcoded credential

opensea-api/references/authentication.md · code · apiKey: "YOUR_API_KEY

Pattern match high

Writes to SKILL.md — self-modifying skill

AGENTS.md · prose · downgraded · SKILL.md` | Write

Pattern match high

HTTP request to bare IP address — common in malicious payloads

opensea-wallet/references/wallet-setup.md · code · http://127.0.0.1

Pattern match medium

Instructs covert action — may act without user awareness

AGENTS.md · prose · downgraded · silently

Pattern match medium

Accesses sensitive environment variables

docs/policy-administration.md · code · process.env.PRIVY_APP_SECRET

Pattern match medium

Base64 encoding/decoding

opensea-wallet/references/wallet-setup.md · code · base64-encode

Pattern match low

Opens WebSocket connection

opensea-api/references/stream-api.md · prose · downgraded · websocket

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API