rdd-decide
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from various local documentation files to drive decision-making and scenario generation, which presents a surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill reads data from
./docs/domain-model.md,./docs/essays/,./docs/product-discovery.md, and the./docs/decisions/directory. - Boundary markers: There are no explicit instructions to treat the content of these files as data only or to ignore embedded instructions (delimiters are absent).
- Capability inventory: The skill possesses the ability to write and edit files in the workspace (
Write,Edit) and can trigger subsequent workflow phases like/rdd-architect. - Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content retrieved from external files before it is processed into the decision-making context.
Audit Metadata