Clawstarter

• Analyzed: May 12, 2026, 3:18 AM
• Findings: 1
• Version: 1.0.2
• Hash: 86cd399491d4e1570edf297179590b551783b29ebf4a5867b48e09861fa42d4a
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill is classified as suspicious due to its self-updating mechanism, high agent autonomy instructions, and execution of external shell commands. The agent is instructed to periodically re-fetch and overwrite its own skill files (SKILL.md, HEARTBEAT.md, DISCOURSE.md) from `https://clawstarter.io` using `curl`, which introduces a supply chain risk if the remote server is compromised. Furthermore, instructions like 'Don't ask permission for routine contributions' encourage autonomous actions, and the skill uses the `gh` CLI tool to create GitHub repositories, representing powerful capabilities that, while currently aligned with the stated purpose, increase the overall risk profile.