content-newsletter
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web sources, which introduces a potential surface for indirect prompt injection.
- Ingestion points: As detailed in
references/newsletter-engine.md, theCuratorrole is responsible for gathering data through "web search for theme-related latest articles, blogs, reports, [and] social media trends." - Boundary markers: The instructions do not specify the use of delimiters or "ignore embedded instructions" warnings when handling the data retrieved from external sources.
- Capability inventory: The skill has the ability to write multiple files to a
_workspace/directory and can interact with external publishing platforms such as WordPress and Typefully through MCP connectors. - Sanitization: Although the workflow includes "Quality Assurance" steps for grammar, tone, and link verification, there are no explicit instructions to sanitize or filter out potential malicious instructions embedded in the external content prior to processing.
Audit Metadata