kirby-panel-and-blueprints
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface as part of its core workflow of reading and interpreting project configurations and documentation.
- Ingestion points: The skill ingests untrusted data from the local environment using
kirby:kirby_blueprint_readand from knowledge base content viakirby:kirby_search. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between data and potential instructions within the ingested content.
- Capability inventory: The skill has the capability to write or modify blueprints and plugin logic (YAML and PHP), which are executable within the Kirby CMS context.
- Sanitization: No specific sanitization or validation steps are outlined for the content read from files or search tools before it is used to generate or modify configurations.
Audit Metadata