map-route
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through the processing of user-supplied journey data.
- Ingestion points: Destination, distance, and duration values provided by the user in the prompt (as described in
SKILL.md). - Boundary markers: No explicit delimiters are used in the instructions to separate user-provided content from instructions.
- Capability inventory: The skill performs file system writes (writing JSON and HTML files) and executes a local Python build script (
build.py). - Sanitization: The destination name is rendered using the
textContentproperty in the Three.js template (template.html), ensuring it is treated as a literal string and preventing script injection in the render context.
Audit Metadata