gsd-audit-uat
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted content from the codebase and UAT documentation files. \n
- Ingestion points: Workspace files and documentation located in
.planning/phases/(specifically-UAT.mdand-VERIFICATION.mdfiles). \n - Boundary markers: Absent; the skill does not define clear delimiters or instructions to isolate ingested data from agent instructions. \n
- Capability inventory: The skill utilizes
spawn_agentto create sub-tasks andrequest_user_inputto interact with the user. \n - Sanitization: Absent; no validation, escaping, or filtering of external content is specified before processing.
Audit Metadata