grill
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from potentially untrusted sources and using that information to drive tool executions and documentation updates.
- Ingestion points: The skill explicitly reads from the user's interview responses and instructs subagents to retrieve data from the codebase or environment (SKILL.md).
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested data are defined.
- Capability inventory: The skill possesses the ability to dispatch subagents for fact-finding and call specific tools (
domain-modeling,to-adr) to perform write operations to the project's glossary and architecture decision records. - Sanitization: The instructions do not specify any validation, escaping, or sanitization of the content retrieved from the codebase or user input before it is used in prompt interpolation or tool arguments.
Audit Metadata