grid-validator
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill audits untrusted JSON files, creating a potential surface for indirect prompt injection.
- Ingestion points: Ingests the full content of target grid body JSON files (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions within the ingested JSON content.
- Capability inventory: The sub-agent is restricted to read-only tools including Read, Grep, and Glob and is forbidden from editing files or network access (SKILL.md).
- Sanitization: The skill does not perform specific sanitization on the JSON data before processing.
- [EXTERNAL_DOWNLOADS]: The skill references several platform-specific component and convention files as authoritative rulebooks for its auditing process (SKILL.md). These references are local to the environment and do not involve untrusted remote sources.
Audit Metadata