newsletter-curation
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a CLI tool and additional skill dependencies from external repositories.
- Evidence: Commands such as
npx skills add belt-sh/cliandnpx skills add inference-sh/skills@email-designare used to extend functionality. - Source: The resources are fetched from the
inference-shandbelt-shrepositories on GitHub, which are associated with the platform provider. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the open web through automated search tools, which could contain adversarial instructions.
- Ingestion points: The skill utilizes search tools (
tavily/search-assistantandexa/search) to pull content from the internet for the newsletter curation process (SKILL.md). - Boundary markers: Absent. The skill does not define delimiters or system-level constraints to isolate retrieved content from the agent's instructions.
- Capability inventory: The skill has the ability to execute shell commands via the
beltCLI, including posting to social media (x/post-create) and running further search applications (SKILL.md). - Sanitization: The instructions include a manual "Curation Quality Filter" checklist that guides the human curator to verify source credibility and relevance, serving as a human-in-the-loop review mechanism.
Audit Metadata