The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing shell commands such as node tools/playwright.js and npx playwright to perform browser automation tasks.
[EXTERNAL_DOWNLOADS]: The skill utilizes npm install and npx to download dependencies and browser binaries from well-known and trusted sources.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from arbitrary external URLs, creating a surface for potential injection attacks.
Ingestion points: The scrape, links, and screenshot commands in SKILL.md allow the agent to ingest content from any provided URL.
Boundary markers: The instructions do not define clear boundaries or provide instructions to the agent to ignore potentially malicious instructions embedded in the scraped content.
Capability inventory: The agent has shell access to execute Node.js scripts and can write files to the local .tmp/ directory.
Sanitization: No sanitization or filtering logic is specified for the data retrieved from external sources.

playwright