system-diagram-generator
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely declarative, consisting of markdown instructions and diagram code templates (Mermaid, PlantUML, and Graphviz).
- [PROMPT_INJECTION]: No instructions were found that attempt to override AI safety guidelines, bypass constraints, or extract system prompts.
- [DATA_EXFILTRATION]: There are no commands to access sensitive files, environment variables, or credentials. No network requests are made.
- [REMOTE_CODE_EXECUTION]: The skill does not include any scripts, package installations (npm/pip), or remote code downloads. The diagram code provided is intended for rendering by the user's interface or documentation tools, not for execution on the host system.
- [COMMAND_EXECUTION]: No subprocess spawning, shell command execution, or privilege escalation patterns (like sudo or chmod) were detected.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user input to generate diagrams, it lacks any dangerous capabilities (such as network access or file writing) that could be exploited via malicious input. The output is limited to text-based diagram definitions.
Audit Metadata