The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions suggest the user configure the chrome-devtools-mcp package via npx in their environment. This is a standard method for utilizing the necessary auditing tools and is consistent with the skill's primary purpose.
[PROMPT_INJECTION]: The skill is designed to process content from external websites, which introduces a surface for indirect prompt injection where malicious content on a visited site could attempt to influence the agent.
Ingestion points: External content is retrieved via navigate_page and take_snapshot as described in the workflow in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions in the ingested data.
Capability inventory: The skill has capabilities for browser navigation, network request inspection, and accessibility tree snapshots.
Sanitization: The workflow does not mention explicit sanitization or filtering of the retrieved web content.

web-perf