The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions guide the agent to fetch and process data from external, potentially untrusted web sources.
Ingestion points: The skill utilizes page.goto and browser.$$eval to navigate to external URLs and extract DOM content as shown in SKILL.md code examples.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or isolate instructions that might be embedded in the scraped web content.
Capability inventory: The skill enables full browser control including navigation, form filling (page.fill), clicking (page.click), network interception (page.route), and screenshot capture.
Sanitization: There are no instructions for sanitizing, validating, or escaping the data extracted from web pages before it is processed by the agent.

browser-automation