uiux-ia-user-flows
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project data which creates a surface for indirect prompt injection. \n
- Ingestion points: The procedure in
SKILL.mdinvolves reading external "product model" and "research implications" files to establish the design context. \n - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore or delimit potentially malicious instructions within the ingested project data. \n
- Capability inventory: The agent is authorized to write and update multiple project documentation files, including
03-information-architecture.mdandhandoffs/structure.md. No network access, arbitrary command execution, or other high-risk capabilities are present. \n - Sanitization: The skill lacks validation or sanitization routines for the data it processes, relying on the agent to interpret the input content directly.
Audit Metadata