kirby-upgrade-and-maintenance
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute project-specific scripts identified during a composer audit and utilizes environment management tools such as
kirby:kirby_runtime_installto synchronize the installation. - [DYNAMIC_EXECUTION]: The workflow involves running scripts discovered at runtime within the project's composer configuration and rebuilding Panel assets for the CMS.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes external configuration files and documentation which could theoretically contain malicious instructions.
- Ingestion points: Local project files
composer.jsonandcomposer.lock, along with remote documentation retrieved via thekirby:kirby_onlinetool (SKILL.md). - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the ingestion of external content.
- Capability inventory: The agent has access to tools for runtime software installation, page rendering, and local script execution (SKILL.md).
- Sanitization: No explicit validation or filtering logic is provided for the contents of external documentation or dependencies.
Audit Metadata