beautiful-article
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process, implement, and review "source material" and information from "external data sources," creating a surface for potential instructions embedded in processed data.
- Ingestion points: The skill ingests user-provided source material and retrieves media or data from external sources via SandBase tools (referenced in
SKILL.mdandreferences/sandbase-api-map.md). - Boundary markers: There are no specific instructions to use delimiters or ignore embedded commands within the ingested source material.
- Capability inventory: The skill is authorized to produce local artifacts (implementations/articles) and invoke SandBase API tools for media generation (
sandbase_run). - Sanitization: The instructions do not specify any sanitization or validation logic for the content retrieved from external sources before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill interacts with the SandBase API to fetch generated media assets such as images, audio, and video. These operations are governed by specific quality gates and require explicit user confirmation for any associated costs.
Audit Metadata