Caveat verdict

liquidskills

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

Hyperliquid dApp development guide that routes to sub-skill files for architecture, gas, wallets, and deployment; purely instructional content about building on a public blockchain with no exfiltration or deceptive behavior.

⚠ 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
70
transparency
70
maintenance

Findings (9)

Pattern match critical

Possible hardcoded credential

indexing/SKILL.md · code · token: '0xSpecificToken

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

tools/SKILL.md · code · curl -L https://foundry.paradigm.xyz | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

tools/SKILL.md · code · | bash

Pattern match medium

Opens WebSocket connection

api/SKILL.md · frontmatter · WebSocket

Pattern match medium

POSTs data to external URL

addresses/SKILL.md · code · .post('https://

Pattern match medium

Instructs covert action — may act without user awareness

api/SKILL.md · prose · downgraded · silently

Pattern match medium

Popular HTTP library — network access

indexing/SKILL.md · code · axios

Pattern match medium

Accesses sensitive environment variables

indexing/SKILL.md · code · process.env.SUPABASE_SERVICE_KEY

Pattern match medium

Python os.environ.get — reads environment variable

orchestration/SKILL.md · code · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

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