zeabur-service-delete
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the AI agent to execute system commands via the Zeabur CLI for service listing and deletion tasks.
- [EXTERNAL_DOWNLOADS]: The skill uses
npx zeabur@latest, which involves downloading and executing the latest version of the Zeabur CLI package from the public NPM registry at runtime. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the interpolation of user-supplied data into shell commands.
- Ingestion points: The
<service-id>,<service-name>, and<project-id>parameters enter the agent's context through user input defined inSKILL.md. - Boundary markers: No delimiters or safety warnings are present to prevent embedded instructions in these fields from influencing the command line.
- Capability inventory: The skill has the capability to execute arbitrary subprocesses via the bash examples provided in
SKILL.md. - Sanitization: No specific sanitization, escaping, or validation logic is defined to protect the shell command strings from maliciously crafted identifiers.
Audit Metadata