kuroco-external-integration-design
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill describes methods for ingesting data from external services (such as Instagram, Slack, and REST APIs) into the Kuroco platform's 'Topics'. This functionality creates a surface for indirect prompt injection, where an attacker-controlled external source could provide malicious instructions that an agent might later process.
- Ingestion points: Data is ingested from external endpoints using the
{api}plugin in Smarty templates (SKILL.md). - Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions when processing or storing external content.
- Capability inventory: The platform configuration supports network requests via the
{api}plugin and database writes/updates via the{api_internal}plugin (SKILL.md). - Sanitization: The documentation does not outline procedures for sanitizing or validating external content to mitigate the risk of instructions being executed by an LLM reading the stored data.
Audit Metadata