notification-platform

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a legitimate technical guide for Sentry developers. All referenced code patterns and internal modules (e.g., sentry.notifications.platform) are consistent with the documented purpose and the authoring organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve creating templates that interpolate data fields into notifications sent to external platforms (Slack, Email, etc.).
  • Ingestion points: Data classes in templates/ and references/data-and-templates.md ingest external strings like error_message and title.
  • Boundary markers: Not explicitly defined in the provided template examples.
  • Capability inventory: NotificationService in SKILL.md enables sending these rendered templates to various communication targets.
  • Sanitization: Standard sanitization is handled by the platform's provider-specific renderers, though not explicitly detailed in this guide.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:56 PM
Security Audit — agent-trust-hub — notification-platform