bd-create-new-product

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses shell commands like 'git init' and 'bd init' to set up a local project environment. These actions are directly aligned with the skill's primary purpose and do not involve suspicious network-to-shell piping or privilege escalation.- [PROMPT_INJECTION] (LOW): Detected surface for indirect prompt injection (Category 8) where untrusted input could influence agent behavior.
  • Ingestion points: Untrusted data enters via '', '', and '' placeholders.
  • Boundary markers: Absent; inputs are interpolated directly into shell command arguments.
  • Capability inventory: The skill can execute git and bd commands, and write to local configuration files (e.g., '.beads/config.yaml').
  • Sanitization: No explicit sanitization or escaping of input variables is defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM