boost-prompt

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill adheres to its stated purpose and uses standard VS Code extension capabilities for user interaction and clipboard operations. No unauthorized network access or suspicious code patterns were detected.
  • [PROMPT_INJECTION]: The skill processes untrusted user input during prompt refinement, which creates a surface for indirect prompt injection.
  • Ingestion points: User input via chat and responses to clarifying questions via the joyride_request_human_input tool.
  • Boundary markers: Absent; the skill does not use specific delimiters to isolate user-provided text from its internal logic.
  • Capability inventory: Includes interactive user requests and system clipboard write access via the Joyride extension's Clojure script interface.
  • Sanitization: None; the skill does not validate or sanitize the content of the refined prompt before displaying it or copying it to the clipboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 05:26 AM