Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
ClawHub Release Manager
v0.1.0Safely release and publish skill updates to ClawHub with version bump discipline. Use when preparing patch/minor releases, running lint/build checks, writing...
⭐ 0· 38·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md explicitly requires running the 'clawhub' CLI and running project checks via 'bun' (bun run lint/build). However, the skill metadata lists no required binaries, no required env vars, and no primary credential. A release manager that runs 'clawhub publish' normally requires the ClawHub CLI and authenticated credentials; those should be declared. The absence of a declared source/homepage (source: unknown) reduces transparency.
Instruction Scope
The instructions stay on-topic: they describe checking authentication, bumping versions, running lint/build, publishing, and returning the release id using a provided output template. They instruct the agent to operate on the local working directory and modify version files and changelogs — expected for a release tool, but this implies the agent will edit repository files and invoke CLI tooling with whatever credentials/config are available in the environment.
Install Mechanism
This is an instruction-only skill with no install spec or code files, which minimizes install-time risk (nothing is downloaded or written by an installer).
Credentials
No environment variables or credentials are declared, but the runtime steps depend on an authenticated 'clawhub' environment (clawhub whoami / clawhub publish). That implies reliance on existing local credentials/config; the skill should declare this dependence so users understand what secrets will be used. No unrelated credentials or unusual environment access are requested.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request to modify other skills or system-wide agent settings. The default ability for the model to invoke the skill autonomously remains, but that is normal and not by itself flagged.
What to consider before installing
This skill appears to implement a reasonable ClawHub release workflow, but there are a few issues to check before installing:
- Tooling: The runtime expects the 'clawhub' CLI and 'bun' (for lint/build). The skill metadata does not declare required binaries. Ensure those tools are installed and available on PATH before using the skill.
- Credentials: Publishing requires ClawHub authentication (the SKILL.md checks 'clawhub whoami'). The skill doesn't declare which credentials it will use; confirm which account/config the agent will use and that you trust it to publish on your behalf.
- Source transparency: The skill has no source or homepage listed. Prefer skills with a public repo or homepage you can inspect. Lack of source increases risk if something goes wrong.
- File changes: The workflow edits version files and changelogs in the working directory. Run this in a branch or ensure you have backups and CI checks; verify the skill's actions on a non-production repo first.
- Operational guardrails: Consider requiring an explicit confirmation step before the skill runs 'clawhub publish' (manual approval), or restricting the agent's environment so it cannot access production credentials inadvertently.
If you need higher assurance, ask the publisher to update metadata to declare required binaries (clawhub, bun/node), list expected credential/config usage, and provide a source repository or homepage for review.Like a lobster shell, security has layers — review code before you run it.
latestvk9741417tp5egq2pjn3mz0s2s58440st
License
MIT-0
Free to use, modify, and redistribute. No attribution required.