prd-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from JIRA issue descriptions and Confluence pages as part of the PRD generation process in workflow-automated-gathering.md. This presents an indirect prompt injection surface. Ingestion points: JIRA issue text and Confluence page content. Boundary markers: Absent. Capability inventory: Local file writing and Confluence page creation. Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill includes and executes a local shell script scripts/collect_prd_info.sh to facilitate user input via macOS system dialogs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:12 AM