waba-template-author

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a Python utility script, scripts/lint_waba_template.py, intended for local execution to validate template JSON payloads against structural and category-specific content rules.\n- [EXTERNAL_DOWNLOADS]: Technical documentation and API endpoints at docs.sent.dm and developers.facebook.com are referenced for legitimate integration support. These domains are recognized as official vendor and well-known service resources respectively.\n- [PROMPT_INJECTION]: The skill ingests user input to draft message templates, representing a surface for indirect prompt injection.\n
  • Ingestion points: User-provided business intent and message content are processed by the agent to generate template drafts. The validation script also reads local JSON files.\n
  • Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within user-provided template content.\n
  • Capability inventory: The skill provides instructions for interacting with the Sent API for template management, including creation, retrieval, and updates.\n
  • Sanitization: A dedicated linter script is provided to detect promotional language in transactional templates and ensure correct placeholder formatting.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 11:39 AM
Security Audit — agent-trust-hub — waba-template-author