Caveat verdict

guardrail-smart-accounts

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

ERC-4337 smart account spending limits for AI agents using transparent, user-controlled policy enforcement at the contract level with clearly declared env vars.

⚠ 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.

33
security
80
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · token: "0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.GUARDRAIL_DASHBOARD_API_KEY

Confirmed in code low

fetch() — outbound network request

SKILL.md · code

Permissions & capabilities

Requires 3 environment variables.

network_outcredential_accessdata_encoding

Is this flag fair?

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