to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes multiple external data sources to generate executable technical specifications, creating a potential surface for instruction injection.
- Ingestion points: Upstream artifacts including
wayfinder.md,decision-log.md,domain-model.md,research-spike.md, andprototype-report.mdare gathered and processed at runtime. - Boundary markers: The procedure lacks explicit delimiters or instructions to ignore embedded commands within the input artifacts.
- Capability inventory: The skill writes to the file system at
docs/tasks/task.<reference>.md. This generated file contains verification commands (e.g.,npm run test) intended for future shell execution. - Sanitization: No sanitization or content validation is performed on the input files before they are synthesized into the final technical plan.
Audit Metadata