zeabur-server-list

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx zeabur@latest to download and run the official Zeabur CLI from the npm registry. This is standard behavior for accessing vendor-provided tooling.
  • [COMMAND_EXECUTION]: The skill facilitates local shell command execution to interface with the Zeabur CLI and provides a mechanism for remote command execution on servers via SSH. These administrative functions are consistent with the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. 1. Ingestion points: The agent ingests data from the output of server list commands and remote SSH sessions as described in SKILL.md. 2. Boundary markers: No explicit boundary markers or isolation instructions are provided for processed data. 3. Capability inventory: The agent can execute local shell commands via the CLI, which is documented in SKILL.md. 4. Sanitization: The skill documentation suggests using grep to filter system banners from SSH output, which provides limited sanitization of remote data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 01:36 PM