graphviz

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as dot, neato, and fdp via the Bash tool to render graph descriptions into image or document files.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection through its data processing workflow.
  • Ingestion points: The agent accepts user input for both the content of the DOT files and the output filenames as described in SKILL.md.
  • Boundary markers: The skill does not define delimiters or provide instructions to the agent to disregard potential instructions embedded in the user-provided graph data.
  • Capability inventory: The skill leverages the Bash, Read, and Write tools to perform operations on the file system and execute programs.
  • Sanitization: There is no guidance on sanitizing or validating user input before it is interpolated into shell commands or written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:19 PM