The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches Mermaid.js and Tailwind CSS from well-known CDNs (jsDelivr and Tailwind's official CDN). These are trusted sources for web assets and are used according to the skill's primary purpose.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use standard OS-level commands such as open (macOS), xdg-open (Linux), and start (Windows) to display the generated HTML report. This is a legitimate use of shell tools to fulfill its visual reporting function.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources like codebases and URLs via a subagent. While this creates an attack surface, the risk is addressed by specifying a narrow focus on structural extraction and enforcing Mermaid's securityLevel: "strict" setting in the HTML scaffold to prevent script injection via diagram definitions.\n- [DYNAMIC_EXECUTION]: The generated HTML contains inline vanilla JavaScript to handle interactions like collapsibles. This logic is self-contained and does not fetch or execute external scripts beyond the specified CDNs.

visual-report