ClawAudit verdict

agentpay-sdk

18
🔴 Dangerous
High-risk patterns flagged for review — automated deep scan, not behaviorally verified.

The skill's use of `executionSinkDetected` flag set to true raises concerns about potential malicious code execution.

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

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

28
security
100
transparency
70
maintenance

Findings (4)

Pattern match critical

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

references/install-and-workflows.md · code · curl -fsSL https://wlfi.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

references/install-and-workflows.md · code · | bash

Pattern match medium

Accesses system credential store

references/install-and-workflows.md · prose · downgraded · Keychain

Pattern match low

References agent configuration files

references/install-and-workflows.md · prose · downgraded · CLAUDE.md

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

Requires 1 system binary.

Is this flag fair?

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