sharpen-query

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and markdown templates. It does not contain any executable scripts, binaries, or automated command-line instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user input to generate refined prompts. While this represents a surface for indirect prompt injection, the skill is scoped to only produce text for the user to review or paste, and it explicitly disables model tool invocation (disable-model-invocation: true), which mitigates the risk of automated exploitation.
  • [EXTERNAL_DOWNLOADS]: The skill references an external YouTube URL for educational context regarding prompt engineering techniques. This is a reference to a well-known service and does not involve automatic downloads or script execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:52 PM
Security Audit — agent-trust-hub — sharpen-query