The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute existing project-level test suites (such as Playwright Test) and internal helper scripts (like browser_preflight.py) to verify environment readiness and route behavior. These actions are within the expected scope of a testing tool.
[INDIRECT_PROMPT_INJECTION]: The skill involves the agent reading and analyzing rendered web page content, such as headings, titles, and console logs, which creates a surface where external content could theoretically influence agent behavior.
Ingestion points: Rendered page content and browser logs are processed during the 'Exercise the routes' phase of the workflow (SKILL.md).
Boundary markers: No specific boundary markers or instructions to ignore embedded directives are defined for the browser-rendered data.
Capability inventory: The skill utilizes shell command execution to interface with browser drivers and local scripts.
Sanitization: No explicit sanitization or filtering of web-rendered content is mentioned prior to agent analysis.
[EXTERNAL_DOWNLOADS]: The skill documentation references a public repository from Every Inc (github.com/EveryInc/compound-engineering-plugin) as a source for its procedures.

browser-smoke