Skill Publisher

Create, validate, security-scan, and publish skills to ClawHub. Use when asked to "make a skill", "publish a skill", "create a new skill", "scaffold a skill"...

This tool generally does what it says (scaffold/validate/scan/publish), but do not run publish.sh blindly. Before using: 1) Inspect SKILL.md (especially the name field) for any suspicious characters; avoid publishing skills whose SKILL.md contains untrusted or unreviewed text. 2) Replace the eval usage in publish.sh with a safer exec model (use an array to call clawhub with arguments) or ensure strict sanitization of slug/name/version inputs. 3) Avoid using --skip-checks or --force unless you understand and accept the risk. 4) Add 'clawhub' to the declared required binaries so users know the dependency. 5) Consider modifying security-scan.sh to also check the core scripts (or have an external reviewer) because it currently skips them. If you cannot review or fix these issues, treat this skill as untrusted and do not use it to publish code to ClawHub.

Type: OpenClaw Skill Name: skillpub Version: 1.0.0 The skill bundle's primary purpose is to create, validate, security-scan, and publish other skills, which is a legitimate function. However, the `scripts/publish.sh` file contains a critical shell injection vulnerability. It constructs a `clawhub publish` command using `eval`, incorporating the `SKILL_NAME` extracted from `SKILL.md`. If an attacker can control the `name` field in a `SKILL.md` file being published, they can inject arbitrary shell commands (e.g., `name: my-skill $(malicious_command)`) that will be executed by `eval` on the system running `publish.sh`. This RCE vulnerability is not detected by the `scripts/security-scan.sh` script, as `publish.sh` is explicitly excluded from its `eval` pattern checks, which is a significant oversight in the security scanner itself.