ClawAudit verdict

skill-auditor-in-sandbox

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill instructs running `curl -fsSL https://novitaclaw.novita.ai/install.sh | bash` to install the CLI, which is a classic curl-pipe-to-shell pattern; while this is a documented prerequisite step rather than covert execution, it fetches and runs untrusted remote code and routes sandbox activity through a third-party cloud service (novita.ai), warranting caution before use.

⚠ 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.

60
security
100
transparency
80
maintenance

Findings (2)

Pattern match high

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

SKILL.md · prose · downgraded · curl -fsSL https://novitaclaw.novita.ai/install.sh | bash

Pattern match high

Pipe to bash — executes piped content as shell commands

SKILL.md · prose · downgraded · | bash

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