Skillv1.0.0

ClawScan security

Nomad Backup · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 13, 2026, 9:20 PM

Verdict: Benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's requirements and instructions align with its stated read-only Nomad monitoring purpose; nothing requests unrelated credentials or installs arbitrary code.
Guidance: This skill appears coherent and read-only: it runs the nomad CLI to list jobs, nodes, allocations, logs, etc. Before installing: 1) Ensure the nomad binary on your system is trusted and up-to-date. 2) If you provide a NOMAD_TOKEN, restrict that token to read-only ACL policy—if the token has write permissions, a malicious agent or misused command could modify cluster state even though the skill's instructions are read-only. 3) Confirm NOMAD_ADDR points to the intended cluster to avoid accidental exposure of other environments. 4) The SKILL.md examples use jq/grep though they aren't declared as required binaries; install those if you need JSON parsing. 5) Verify the skill source (homepage repo and owner) yourself if you need a higher assurance level—_meta.json ownerId in the package metadata differs from the registry owner id in the manifest, which is worth double-checking but may be a benign metadata mismatch.

Purpose & Capability: okThe skill is an instruction-only Nomad client: it requires the nomad CLI (declared) and its commands map directly to listing jobs, nodes, allocs, etc. No unrelated binaries, services, or credentials are requested.
Instruction Scope: noteSKILL.md confines itself to read-only nomad CLI commands. It references environment variables used by the Nomad CLI (NOMAD_ADDR, NOMAD_TOKEN, cert paths), and shows examples that pipe JSON into jq or grep (jq/grep are not declared as required binaries). Be aware that reading allocation logs or agent info can expose sensitive application data—this is consistent with a monitoring skill but is a privacy consideration, not an incoherence.
Install Mechanism: okNo install spec or code is included; this is instruction-only and relies on an existing nomad binary. That minimizes supply-chain risk.
Credentials: okThe SKILL.md lists only Nomad-related env vars (NOMAD_ADDR, NOMAD_TOKEN, NOMAD_NAMESPACE, region and TLS cert paths). These are proportionate to the stated purpose. Note: a provided NOMAD_TOKEN could have broader privileges than intended—the skill does not request unrelated secrets.
Persistence & Privilege: okThe skill is not always-enabled and does not request persistent system changes or access to other skills' configs. It is user-invocable and can be called autonomously (normal platform behavior).