kirby-debugging-and-tracing
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes content from the CMS that may be untrusted.
- Ingestion points: Data enters the agent's context through
kirby:kirby_render_pagein step 3 andkirby:kirby_dump_log_tailin step 5 of the workflow (SKILL.md). - Boundary markers: The instructions do not define delimiters or specific "ignore" instructions for the agent when processing the output from rendering or log-reading tools.
- Capability inventory: The skill can execute powerful tools including
kirby:kirby_runtime_install,kirby:kirby_init, and tools to index and potentially readtemplates,snippets,controllers,models, androutes(SKILL.md). - Sanitization: There is no evidence of sanitization or content validation performed on the rendered output or log data before it is processed by the agent.
Audit Metadata