grill-system-design
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a user-facing interview process for system design, which creates an ingestion point for untrusted data. * Ingestion points: User responses during the system design interview initiated in SKILL.md. * Boundary markers: The instructions explicitly mandate applying the [question boundary] from the grill-to-spec skill to manage user interactions. * Capability inventory: The skill acts as a high-level orchestrator for design-by-contract and grill-to-spec; no shell commands, network requests, or file writes are present in this skill. * Sanitization: Employs boundary enforcement as defined in the referenced external specification.
- [NO_CODE]: This skill consists entirely of instructional markdown and metadata, with no associated scripts or executable components provided.
- [SAFE]: No indicators of malicious intent, prompt injection, data exfiltration, or obfuscation were found. The skill follows best practices by enforcing interaction boundaries.
Audit Metadata