The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and parses test result data from test-output.log and Playwright's JSON reporter. If a test case name or a captured error message contains malicious instructions, they could influence the agent's subsequent analysis or reporting steps.
Ingestion points: Reads output from npx playwright test and files in test-results/ and playwright-report/.
Boundary markers: The skill does not implement specific delimiters or warnings to the agent to ignore potentially malicious content within test logs.
Capability inventory: The skill can execute shell commands (npx, curl), write to the file system, and perform network operations.
Sanitization: No sanitization or filtering is performed on the extracted test names or error messages before they are processed by the agent.
[COMMAND_EXECUTION]: The skill executes several shell commands to manage the test lifecycle.
Runs tests and generates reports using npx playwright test.
Lists directory contents using ls -la to verify result existence.
Uses curl to send test summaries to a user-defined Slack webhook.
[EXTERNAL_DOWNLOADS]: The skill uses npx playwright, which may fetch the Playwright framework and necessary browser binaries from Microsoft's official package registries. This is a standard and expected operation for this tool.

report