The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute open (on macOS) or xdg-open (on Linux) to launch the generated HTML report in the user's default browser.
[EXTERNAL_DOWNLOADS]: The skill fetches the Mermaid JS library from the well-known jsdelivr.net CDN to render diagrams within the generated HTML report.
[PROMPT_INJECTION]: The skill processes untrusted data from repository files and conversation history to generate report content, presenting an indirect injection surface.
Ingestion points: Repository findings, analysis artifacts, and recent agent output extracted via Read, Glob, and Grep tools.
Boundary markers: No specific delimiters or instructions are provided to the agent to treat interpolated findings as data rather than instructions.
Capability inventory: The skill possesses the capability to write files to the local system and execute shell commands to open those files in a browser context.
Sanitization: The instructions do not define requirements for escaping or sanitizing the content before it is embedded into the HTML structure, which could lead to malicious HTML or scripts being executed when the user opens the report.

atlas-report