The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill navigates to and extracts data from arbitrary web pages, which creates a surface for indirect prompt injection attacks. Malicious instructions embedded in the content of visited websites could attempt to influence the agent's subsequent actions.
Ingestion points: Web content accessed via browser_navigate and processed through scraping workflows in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions found within scraped data.
Capability inventory: The skill utilizes tools for clicking, typing, and navigation, allowing the agent to perform actions based on the data it reads.
Sanitization: There is no evidence of sanitization or filtering applied to the extracted web content before it is processed by the agent.
[DYNAMIC_EXECUTION]: The skill accepts 'Scripts' as input and provides JavaScript examples for browser control. While this is the intended functionality for Puppeteer/Playwright automation, executing dynamically generated scripts involves inherent risks if the logic is influenced by untrusted external data.

Browser Automation