The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands to perform its quality assurance tasks. Specifically, it uses ls -la to verify directory structures, grep to search for specific design patterns or keywords in source files, and executes a local script ./qa-playwright-capture.sh to trigger automated browser testing.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external sources, which creates a surface for indirect prompt injection if those sources are compromised.
Ingestion points: Reads data from public/qa-screenshots/test-results.json and interprets visual content from generated screenshots.
Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the data read from the JSON results file.
Capability inventory: The agent has the capability to execute shell commands (ls, grep, script execution) and read file contents.
Sanitization: There is no explicit sanitization logic for the content read from test-results.json before it is processed by the agent's logic.

Reality Checker