newsletter-curation

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI to perform automated search and content generation tasks. Execution is correctly scoped to the belt tool via the allowed-tools configuration.
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and related skill packages from the official inference-sh GitHub organization. These represent standard platform dependencies and do not represent a security risk.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external search results (Tavily and Exa). This is inherent to the curation functionality. Ingestion points: External search results processed via belt app run. Boundary markers: Not present in the provided command examples. Capability inventory: Bash tool access restricted to the belt CLI namespace. Sanitization: No explicit sanitization or filtering is described in the prompt construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:27 PM
Security Audit — agent-trust-hub — newsletter-curation