boost-prompt

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (mkdir -p .aix) to manage a dedicated local directory for its generated artifacts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate a refined prompt, which is then placed on the system clipboard and written to local files.
  • Ingestion points: User-provided task scope, objectives, and deliverables.
  • Boundary markers: Absent.
  • Capability inventory: Local file writing, directory creation, and system clipboard access.
  • Sanitization: None. While the skill lacks explicit sanitization or boundary markers, the behavior is within the expected functionality of a prompt engineering utility.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:22 AM
Security Audit — agent-trust-hub — boost-prompt