kirby-performance-and-media
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted template data which could contain hidden instructions designed to manipulate the agent's behavior during the optimization process. \n
- Ingestion points: Template content accessed via
kirby:kirby_templates_indexandkirby:kirby_snippets_index, as well as Knowledge Base search results. \n - Boundary markers: None identified; there are no specific delimiters or instructions for the agent to ignore embedded content within the analyzed files. \n
- Capability inventory: The skill utilizes capabilities such as reading system configuration (
kirby://config/cache), listing files, searching knowledge bases, and rendering pages throughkirby:kirby_render_page. \n - Sanitization: No sanitization or validation of the template content is specified in the workflow.
Audit Metadata