zeabur-update-service
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information like project IDs, service IDs, and environment variable values by embedding them directly into shell commands. This creates a surface for potential indirect prompt injection or command injection attacks if the input is malicious.
- Ingestion points: User inputs for
<project-id>,<service-id>, environment variable keys/values, and image tags in SKILL.md. - Boundary markers: No delimiters or explicit instructions are used to distinguish untrusted user data within the command strings.
- Capability inventory: The skill executes shell commands using
npx zeabur@latestfor tasks like listing services and updating variables. - Sanitization: No sanitization or validation steps are provided to check the user-supplied values before they are executed.
- [COMMAND_EXECUTION]: The skill instructs the agent to run multiple shell commands to list, modify, and restart services.
- [EXTERNAL_DOWNLOADS]: The skill uses
npx zeabur@latestto download and execute the vendor's official command-line interface from the public npm registry.
Audit Metadata