kata-showme
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project context to generate visual explanations, creating a surface where malicious content in files could influence the agent.
- Ingestion points: Reads 'topic-context' and 'explanation-request' in SKILL.md.
- Boundary markers: Lacks explicit instructions or delimiters to isolate processed data from the agent's core instructions.
- Capability inventory: Writes local HTML files and initiates file previews (SKILL.md).
- Sanitization: No validation or sanitization is mentioned for data interpolated into the generated HTML artifacts.
- [DYNAMIC_EXECUTION]: Generates and opens local HTML files based on user-provided data.
- Evidence: Instructs the agent in SKILL.md to 'write one focused HTML file' and 'open it with the host's file preview or browser'.
Audit Metadata