novu-manage-subscribers

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted subscriber data such as names, emails, and custom metadata, along with notification payloads which are processed by the Novu notification engine.
  • Ingestion points: Subscriber profile fields and trigger payloads in SKILL.md and references/subscriber-crud-examples.md.
  • Boundary markers: None present in the code snippets to delimit untrusted data from instructions.
  • Capability inventory: The skill performs network operations to the Novu API but lacks local execution capabilities such as eval, exec, or shell command execution.
  • Sanitization: No explicit validation or sanitization of input data is demonstrated in the provided examples.
  • [EXTERNAL_DOWNLOADS]: The skill references official vendor libraries for integration, which is standard for its intended purpose.
  • References @novu/api for Node.js environments.
  • References novu_py for Python environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:03 AM