The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands to start local development servers (e.g., npm run dev, yarn dev) to host the application during verification.
[DATA_EXFILTRATION]: Uses the upload_html_report tool to send UI session artifacts, including video recordings and traces, to Shiplight's cloud service for report sharing.
[CREDENTIALS_UNSAFE]: Provides a mechanism to save browser session state, including cookies and localStorage, to the local file system at ~/.shiplight/ via the save_storage_state tool.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external web content.
Ingestion points: The agent ingests the page DOM and screenshots using the inspect_page tool.
Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the page content.
Capability inventory: The agent has access to powerful interaction tools (act), log retrieval, and remote data uploading (upload_html_report).
Sanitization: No sanitization of the DOM content is performed prior to analysis.

verify