astrofy-routing
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing the
astrofyCLI tool (astrofy check --category routing) to perform routing checks. This is a functional requirement for validating the project's route configuration. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from local project files, creating a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The
src/pagesdirectory, the return objects fromgetStaticPaths, and the.astrofy/config/paths.jsonconfiguration file. - Boundary markers: No explicit delimiters or instructions to treat ingested content as untrusted are provided in the prompts.
- Capability inventory: The skill possesses the capability to execute the
astrofycommand-line utility for validation tasks. - Sanitization: There are no specified sanitization or validation steps for the content read from these files.
- [EXTERNAL_DOWNLOADS]: The skill provides links to the official Astro documentation for routing and implementation details. These are well-known and trusted technical resources.
Audit Metadata