mermaid-diagram-generator
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a Python utility (
scripts/generate_diagram.py) for the agent to execute. This script automates the extraction of program logic from Arduino source files and generates Mermaid diagram syntax. - [INDIRECT_PROMPT_INJECTION]: The skill's automated generator reads and processes user-provided source code, creating a surface for indirect prompt injection where malicious content in the code could affect the output.
- Ingestion points:
scripts/generate_diagram.pyreads files via the--inputflag or interactive user prompts (line 103, 155). - Boundary markers: No specific delimiters or warnings are used when reading source file content to instruct the model to ignore embedded instructions.
- Capability inventory: The script can read local files, write output to specified file paths, and print to the terminal.
- Sanitization: The script uses regular expressions to extract specific patterns (enums, defines, and state assignments), which inherently limits the type of data processed to alphanumeric characters and underscores.
Audit Metadata