sendcutsend

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches current manufacturing guides and engineering specifications directly from cdn.sendcutsend.com. These references are used as the ground truth for manufacturing readiness reports.
  • [COMMAND_EXECUTION]: Executes Python code using the build123d and ezdxf libraries to perform local geometry inspections, such as measuring part dimensions, hole sizes, and flange depths from user-provided CAD files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from both user-uploaded CAD files (DXF/STEP) and external web sources (JSON/Markdown from SendCutSend).
  • Ingestion points: CAD files (DXF/STEP) in SKILL.md and remote configuration files defined in references/official-sources.md.
  • Boundary markers: Instructions specify that source data should be treated as "evidence feeds" rather than executable logic, and the agent is cautioned to handle missing or conflicting data without assuming success.
  • Capability inventory: The skill uses Python for geometric analysis and generates reports based on comparisons.
  • Sanitization: The skill mandates defensive parsing (e.g., handling numeric strings, size strings, and N/A values) to ensure data integrity during comparison.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 10:00 PM