The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill generates a local HTML file (/tmp/timeline.html) at runtime using a predefined template. It then executes this file by opening it in a browser via Chrome DevTools. This involves dynamically building JavaScript data structures from the current project context to populate the visualization.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted sources, creating a potential surface for indirect injection if malicious data is present in the analyzed files.
Ingestion points: The skill processes data from git-diff, repository files, and user questions as specified in the frontmatter and workflow.
Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to isolate the ingested data when inserting it into the HTML script template.
Capability inventory: The agent uses the Write tool to create local files and mcp__chrome-devtools to interact with a browser instance.
Sanitization: The instructions do not define sanitization or escaping steps for the content extracted from the context before it is embedded into the HTML's JavaScript block.
[EXTERNAL_DOWNLOADS]: The HTML template in TEMPLATE.md references the vis-timeline library (both CSS and JavaScript) from cdnjs.cloudflare.com. This is a well-known and trusted content delivery network, and the reference is required for the intended visualization functionality.

timeline