chkit-ingestion
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the development of API ingestion sources that fetch data from external providers. This establishes a surface for indirect prompt injection if the ingested data contains malicious instructions that are later processed by an agent.
- Ingestion points: Data streams, readers, and API responses from external providers (SKILL.md).
- Boundary markers: None specified for the ingested record content in the implementation guide.
- Capability inventory: Access to ClickHouse configurations and the ability to perform networked HTTP requests via the chkit context (SKILL.md).
- Sanitization: The instructions do not explicitly mandate sanitization or filtering of the external content being ingested before storage or retrieval.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official documentation and quickstart guides on the vendor's site.
- Sources: References documentation and API guides at
chkit.obsessiondb.com.
Audit Metadata