notifications

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and source code from FacteurJS on GitHub, the official AdonisJS documentation, and MDN Web Docs for SSE specifications.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill describes processing external data through OrderShippedParams (e.g., orderId, trackingUrl) which are used to construct notification content in SKILL.md.
  • Boundary markers: No specific delimiters or boundary markers are utilized to isolate untrusted notification content from agent instructions.
  • Capability inventory: The skill environment provides the agent with access to potentially powerful tools including Bash, Write, and Edit.
  • Sanitization: The provided code examples do not include explicit sanitization or validation of the external parameters before they are persisted or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 01:05 PM
Security Audit — agent-trust-hub — notifications