prd-studio

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface through its handling of external data.
  • Ingestion points: User requirements and BRD files are directly interpolated into subagent prompts during the initialization and Writer phases.
  • Boundary markers: Absent; the prompts for the subagents lack delimiters or specific instructions to ignore instructions embedded within the processed source files.
  • Capability inventory: The agent has file system access (read/write) and can execute shell commands via bash.
  • Sanitization: No sanitization or validation of input data is performed before it is used to drive agent behavior.
  • [COMMAND_EXECUTION]: The skill uses shell commands for workspace setup.
  • Evidence: The initialization phase executes mkdir -p workflow/ to establish a directory for state and document storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 09:42 PM