tool-foundation-sprint-approach-options
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and template-based. It defines a human-facilitated process for product ideation and does not include any scripts, commands, or network-facing tools.
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting artifacts from previous sprint phases (Basics and Differentiation). While this represents a data ingestion surface, the skill has no associated tool capabilities or system access that could be leveraged for malicious purposes.
- Ingestion points: Ingests "Basics bundled artifact" and "Differentiation bundled artifact" as specified in the Inference Inputs table in SKILL.md.
- Boundary markers: The process includes specific framing steps and a Decider Checkpoint to validate that inputs and outputs remain within the strategic scope.
- Capability inventory: No subprocess execution, network requests, or sensitive file system operations are present in the skill definition.
- Sanitization: The skill relies on facilitator review and decider sign-off rather than automated sanitization, which is appropriate for its intended ideation use case.
Audit Metadata