The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the chrome-devtools-mcp package from the NPM registry to provide its core performance auditing capabilities.
[COMMAND_EXECUTION]: The skill requests and uses the Bash tool to perform local codebase analysis, such as identifying framework configurations (e.g., Webpack, Vite, Next.js) and auditing build scripts.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and analyze untrusted data from external sources.
Ingestion points: The agent retrieves and processes arbitrary external web content using the navigate_page and performance_start_trace tools (SKILL.md).
Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions that might be embedded within the HTML or DOM of the target websites.
Capability inventory: The agent is granted access to the Bash, Read, Grep, and Glob tools, which could be leveraged if the agent inadvertently follows instructions found on a malicious webpage.
Sanitization: No evidence of sanitization, filtering, or validation of the retrieved web content is present in the skill's logic.

web-perf