sendcutsend

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches official manufacturing specifications and design guides from https://cdn.sendcutsend.com. These are legitimate data sources required for the skill's DFM (Design for Manufacturing) functionality.
  • [COMMAND_EXECUTION]: The skill uses a bundled Python script (scripts/download_sources.py) to manage the downloading and caching of these external reference files. This is a standard automation pattern for AI agent skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown and JSON data which introduces a minor attack surface. Ingestion points: references/generated/sendcutsend-ordering-guide.md, sendcutsend-catalog.json, and sendcutsend-specs.json. Boundary markers: Explicit instructions are provided to treat the data as evidence feeds rather than instructions, though technical delimiters are not used. Capability inventory: Uses scripts/download_sources.py (shell execution) and $cad tools. Sanitization: No specific sanitization or filtering of the external content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 02:12 PM
Security Audit — agent-trust-hub — sendcutsend