SkillReported removedCoverage: CoveredPrimary source

More skills by zaycv: linkedin-job-application, autoupdater, deepresearch

Reported by Community reports on GitHub (adrianwedd, hendrysadrak, rafadiasbsb) on . Names, numbers, and dates are as the sources state them.

What it did

Skills from the same publisher used a fake required “driver” or installer: an obfuscated macOS command that fetched code from a raw IP address, and a password-protected archive for Windows. The linkedin-job-application report says the command appeared four times in one SKILL.md, including a variant run with sudo.

Skill names as reported

  • linkedin-job-application
  • autoupdater
  • deepresearch

Techniques

  • Fake prerequisite
  • Encoded command
  • Download piped to shell
  • Password-protected archive

Status, as stated by the source

On 13 March 2026 an OpenClaw maintainer wrote on each issue that the publisher is banned or hidden and the reported skills are no longer public.

We do not check the registry ourselves. “Unknown” means no source we found says the skill was removed.

Would Ironheights flag this pattern?

Covered

The inline decode-and-run line is flagged by IH-EXEC-001 (critical, so the verdict is block), the sudo variant also by IH-PRIV-001, and the decoy installer host by IH-NET-001. The Windows archive link is not flagged.

Rules that fire on a harmless, synthetic copy of the reported pattern. We did not scan the original malware, and a rule firing on the pattern is not a promise about every variant.

Sources

  1. openclaw/clawhub issue #124: Malicious skill linkedin-job-application by zaycv contained RCE payload(opens in a new tab)GitHub (openclaw/clawhub issue tracker) · primary
  2. openclaw/clawhub issue #138: Malicious skill ‘autoupdater’ contains malware payload(opens in a new tab)GitHub (openclaw/clawhub issue tracker) · primary
  3. openclaw/clawhub issue #154: Malicious skill distributing malware - zaycv/deepresearch(opens in a new tab)GitHub (openclaw/clawhub issue tracker) · primary

Sources are the only outbound links on this page. We never link to the skills themselves or publish their payloads.

Rules that look at neighbouring patterns. They are listed for reading, not as coverage of this entry.