skills/atxinsky/skills/distill/Gen Agent Trust Hub

distill

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve analyzing external codebase content to identify simplification opportunities, which introduces a common surface for indirect prompt injection. \n
  • Ingestion points: Reads context from the current thread and codebase to evaluate design complexity. \n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present. \n
  • Capability inventory: The skill uses tool calling (AskUserQuestionTool) and is designed to perform code/layout modifications. \n
  • Sanitization: No sanitization of ingested code or design files is described. \n- [SAFE]: No instances of prompt injection, credential harvesting, or unauthorized network communication were detected. \n- [SAFE]: The skill does not use any obfuscation techniques or remote code execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 04:00 PM
Security Audit — agent-trust-hub — distill