design-orchestration
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided feature proposals and designs to orchestrate workflows, creating an attack surface where malicious content in these documents could attempt to manipulate routing decisions or bypass review stages.\n
- Ingestion points: Design proposals and feature descriptions referenced in the
SKILL.mdrouting logic.\n - Boundary markers: Absent; there are no instructions to the agent to treat external content as data only or to ignore embedded instructions.\n
- Capability inventory: Directs workflow between
brainstormingandmulti-agent-brainstormingskills and determines if implementation can proceed.\n - Sanitization: Absent; no validation or filtering is applied to the incoming design artifacts.\n- [NO_CODE]: The skill consists entirely of instructional markdown and does not include any scripts, executables, or code files.
Audit Metadata