workflow

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the management of Treasure Data projects and workflows through the tdx CLI. It includes commands for project synchronization (pull, push, clone), workflow execution (run, retry), and platform monitoring (sessions, attempts, timeline). These operations are consistent with the primary purpose of a developer tool for workflow automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes workflow definition files and logs, which could potentially contain malicious instructions.
  • Ingestion points: Reads local workflow manifests (.dig files) via workflow_get and remote task logs via tdx wf attempt <id> logs.
  • Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the content of manifests or logs.
  • Capability inventory: The skill allows the agent to modify platform secrets, delete projects, and trigger workflow runs via the tdx CLI.
  • Sanitization: No explicit sanitization or validation of the ingested manifest or log content is described.
  • [EXTERNAL_DOWNLOADS]: The skill uses tdx wf pull and tdx wf download to fetch workflow project files from the Treasure Data platform. These are standard synchronization operations from the vendor's official infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 07:21 AM
Security Audit — agent-trust-hub — workflow