Back to skill
Skillv1.0.0
ClawScan security
JobTread Agent · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 13, 2026, 9:09 PM
- Verdict
- benign
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The instructions match the stated purpose (calling JobTread's Pave API) and no unexpected installs or unrelated credentials appear, but the SKILL.md expects you to store/use a local grant key file even though the skill metadata declares no config paths — a minor documentation/metadata mismatch you should note before installing.
- Guidance
- This skill appears to be what it says: instructions for calling JobTread's Pave API. Before installing, decide how you will store the grant key — SKILL.md recommends a local file (~/.config/jobtread/grant_key). If you prefer stronger controls, use a platform secret store or an env var rather than an unencrypted file. Confirm you are comfortable the skill will read that file and will send the key only to https://api.jobtread.com/pave as shown. Rotate the grant regularly, restrict webhook endpoints to trusted URLs, and avoid copying the grant key into chat or logs. Finally, note the metadata omission (no declared config paths) — ask the publisher to clarify where and how the skill will access the grant key if you need an explicit assurance.
Review Dimensions
- Purpose & Capability
- okThe skill's name and description claim to operate JobTread via its Pave API and the SKILL.md contains detailed, focused examples and payload formats for creating/reading/updating JobTread resources — these requirements are coherent with the stated purpose.
- Instruction Scope
- noteRuntime instructions explicitly require a JobTread grant key and show how to store it at ~/.config/jobtread/grant_key, how to include it in POST payloads, and how to manage webhooks. The instructions do not ask the agent to read unrelated files or exfiltrate data. However, the skill metadata lists no required config paths even though SKILL.md expects a local config file — a documentation mismatch to be aware of.
- Install Mechanism
- okThere is no install spec and no code files — this is instruction-only and does not download or write code to disk, which minimizes install-related risk.
- Credentials
- noteNo environment variables or credentials are declared in metadata, but the operational instructions require a sensitive grant key. Requesting a single service-specific grant key is proportionate to the API use, but the skill relies on a local secret file rather than declared secrets or a platform-managed secret — consider whether you prefer using a secrets store or environment variable instead of a plaintext file.
- Persistence & Privilege
- okThe skill is not always-enabled and does not request system-wide or cross-skill configuration changes. Autonomous invocation is enabled by default (normal), and there are no indicators it will modify other skills or global agent settings.