causal-loop-diagram-generator
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's rendering components (
cld-inline.jsandmain.html) fetch thevis-networklibrary from a well-known service (unpkg.com) at a pinned version (10.0.1). This is a common and appropriate method for including visualization dependencies in web-based documentation. - [DATA_EXFILTRATION]: The skill includes a 'Save Positions' feature in
cld-viewer.jsthat allow users to download updated configuration or copy it to the clipboard. These actions are performed locally within the browser context to facilitate user-driven layout adjustments; no unauthorized external transmissions were identified. - [COMMAND_EXECUTION]: The skill instructions focus on generating JSON and Markdown files and updating the
mkdocs.ymlconfiguration. These operations are consistent with the skill's primary purpose of automating documentation tasks and do not involve high-risk shell commands or privilege escalation. - [PROMPT_INJECTION]: The skill instructions are clearly defined and focused on diagram generation. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.
Audit Metadata