The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to run tests (npx playwright test) and view reports (npx playwright show-report) to provide feedback to the user.
[DATA_EXFILTRATION]: Test results are sent to an external Slack webhook using the curl command and the SLACK_WEBHOOK_URL environment variable. While this is the intended functionality for the user, it involves transmitting data to a non-whitelisted external endpoint.
[INDIRECT_PROMPT_INJECTION]: The skill parses and processes test names and error messages which can be influenced by external code or inputs during the testing process. This content is then presented to the agent without sanitization or protection.
Ingestion points: Test output logs and JSON reports generated by Playwright as described in SKILL.md.
Boundary markers: No delimiters or safety instructions are used when the agent handles the interpolated test failure data.
Capability inventory: Shell command execution (npx), network access (curl), and file system operations (ls, tee) are available to the skill in SKILL.md.
Sanitization: The skill does not perform any escaping or validation on test failure descriptions or names before they are included in the generated reports.

report