newsletter-curation

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the belt-sh/cli tool and additional skills such as inference-sh/skills@email-design using the npx command. These represent external package dependencies from sources not specifically listed as trusted.
  • [COMMAND_EXECUTION]: The documentation provides examples of shell commands using the belt CLI to run applications that perform web searches, generate assets, and post to social media.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external search providers (Tavily, Exa) into the agent's workflow. Ingestion points: Search results from Tavily and Exa referenced in SKILL.md. Boundary markers: No explicit delimiters or instructions are used to isolate untrusted search content in the provided templates. Capability inventory: Shell command execution through the belt CLI is allowed. Sanitization: No sanitization or validation of the retrieved content is mentioned, which could allow malicious source material to influence the agent's subsequent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — newsletter-curation