cad-dxf-agent

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the cad-ai-agent Python package from the author's GitHub repository (github.com/jeremylongshore/cad-ai-agent.git) using pip if the utility is not already installed on the system.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute cad-analyze and cad-revision commands. These tools are used to perform deterministic analysis of DXF drawings, such as compliance checks, health audits, and quantity takeoffs.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external DXF files.
  • Ingestion points: DXF files located via Glob or provided by the user.
  • Boundary markers: None identified in the prompt instructions.
  • Capability inventory: Bash (command execution), Read, and Glob tools are accessible.
  • Sanitization: Findings are parsed from JSON output and reported in prose, which reduces but does not entirely eliminate the risk of the agent interpreting embedded malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:41 AM
Security Audit — agent-trust-hub — cad-dxf-agent