The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests content from external test results which could contain untrusted data in the form of failure messages or error logs.
Ingestion points: Reads results from test-output.log and Playwright JSON reports.
Boundary markers: No explicit delimiters are used in the markdown templates to distinguish between instructions and data.
Capability inventory: The skill possesses shell execution capabilities (npx, curl) and file writing permissions.
Sanitization: Test failure strings are interpolated directly into reports without explicit sanitization or filtering.
[COMMAND_EXECUTION]: Executes shell commands to perform standard testing and reporting tasks.
Evidence: Utilizes npx playwright test to run test suites and npx playwright show-report for visualization.
[DATA_EXFILTRATION]: Forwards test status summaries to external endpoints.
Evidence: Sends test data to Slack via curl using a URL provided by environment variables.

report