assemblyai-webhooks-events

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external webhook payloads from AssemblyAI, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Webhook callback payloads are processed via bound routes as described in the instructions of SKILL.md.
  • Boundary markers: The skill requires strict verification of the Authorization header and validation of allowlisted fields to distinguish trusted metadata from untrusted input.
  • Capability inventory: The skill utilizes standard file system tools (Read, Glob, Grep, Write, Edit) for repository inspection and implementation.
  • Sanitization: Instructions specify capturing bounded raw bytes, validating content types, and implementing quarantine for schema drift to ensure data integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 04:49 AM
Security Audit — agent-trust-hub — assemblyai-webhooks-events