skills/i9wa4/dotfiles/diagramming/Gen Agent Trust Hub

diagramming

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local CLI tools such as drawio, git, and mmdc (Mermaid CLI) to process diagram files and stage changes. These tools are used for their intended purpose within the workflow defined in the scripts convert-drawio-to-png.sh and the documentation in mermaid.md.
  • [EXTERNAL_DOWNLOADS]: The documentation references external resources for diagramming best practices and icon sets, including official AWS documentation and well-known community repositories such as jgraph/drawio. These references are informative and do not involve silent background downloads or executions.
  • [DATA_EXFILTRATION]: No evidence of sensitive data access or network exfiltration was found. The skill operates primarily on local diagram source files and scripts do not contain network-outbound logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes structured data formats like XML (.drawio) and Mermaid source files.
  • Ingestion points: .drawio (XML) and .svg files are processed by check-drawio-svg-overlaps.mjs.
  • Boundary markers: None explicitly defined for safety, but processing is limited to local file system targets.
  • Capability inventory: File reading, writing, and execution of local diagramming CLI tools.
  • Sanitization: The scripts use basic regex for parsing and standard shell quoting for CLI arguments. The risk is considered low as the tools are specialized for diagram rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 01:19 PM
Security Audit — agent-trust-hub — diagramming