skills/celigo/ai/building-b2b/Gen Agent Trust Hub

building-b2b

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is primarily instructional documentation and schema definitions for the Celigo B2B Manager. All external resources, including CLI tools and documentation links, belong to the official 'celigo' vendor ecosystem.
  • [COMMAND_EXECUTION]: The skill documents the use of the celigo CLI for administrative tasks such as creating EDI profiles, file definitions, and connections, as well as monitoring transaction logs and downloading job files.
  • [PROMPT_INJECTION]: The skill has a surface area for indirect prompt injection because it retrieves and processes data from external EDI transactions and trading partner configurations.
  • Ingestion points: Data is ingested via celigo edi-transactions list and celigo tp-connectors list as described in SKILL.md.
  • Boundary markers: Absent; there are no explicit instructions to isolate processed data from the agent's control logic.
  • Capability inventory: The skill has broad capabilities through the celigo CLI, including resource modification and file downloads via celigo jobs download-files in SKILL.md.
  • Sanitization: Absent; no sanitization or escaping of the fetched data is specified in the skill body.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:09 AM
Security Audit — agent-trust-hub — building-b2b