tilebox-workflow-jobs

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the tilebox CLI to manage jobs and clusters. It also includes an example of generating a Python script locally to serialize task data.
  • [PROMPT_INJECTION]: The skill facilitates the processing of external data via the --input and --input-file flags in the tilebox job submit command, creating a surface for indirect prompt injection.
  • Ingestion points: Data provided to the --input and --input-file flags in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or warnings for the agent to use when handling this data.
  • Capability inventory: Execution of the tilebox CLI for job submission, state inspection, and lifecycle management (cancel/retry).
  • Sanitization: There are no instructions for the agent to sanitize or validate the external input before submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 09:17 AM
Security Audit — agent-trust-hub — tilebox-workflow-jobs