skills/shipshitdev/skills/shape/Gen Agent Trust Hub

shape

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely descriptive and instruction-based, intended to guide the AI's logic during a design discovery phase. It does not include scripts, binaries, or complex command execution.
  • [COMMAND_EXECUTION]: The skill uses file-read operations to gather context from standard documentation files like PRODUCT.md and DESIGN.md. These are benign read operations for project grounding.
  • [EXTERNAL_DOWNLOADS]: The documentation references an upstream repository on GitHub for attribution and version tracking purposes, but the skill itself does not perform any remote fetches or downloads at runtime.
  • [PROMPT_INJECTION]: The instructions are clear and professional, focusing on UX methodology (Discovery Interview and Design Brief) without any attempts to override model safety filters or bypass constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:08 PM
Security Audit — agent-trust-hub — shape