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.md and -VERIFICATION.md files). \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_agent to create sub-tasks and request_user_input to interact with the user. \n
  • Sanitization: Absent; no validation, escaping, or filtering of external content is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:33 AM