decompose-research-goal
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an input contract that accepts untrusted external data.
- Ingestion points: Data is ingested via
research_direction,constraints,actor_profile, andobstacle_reportfields defined in the SKILL.md file. - Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential prompt injection patterns within the user-provided data.
- Capability inventory: The skill orchestrates multiple sub-skills (
formulate-top-goal,decompose-and-or-goal,validate-goal-tree,assess-goal-feasibility,map-dependencies,crystallize-north-star) to process and generate research outputs. - Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the incoming research data.
- [NO_CODE]: The skill contains only markdown instructions and configuration metadata. It does not include or execute any scripts, binaries, or shell commands directly.
Audit Metadata