The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard system utilities and Node.js one-liners to locate and extract data from local test reports.
Evidence: SKILL.md includes commands such as find, cat, jq, and node -e to process mochawesome.json and results.xml files.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from test reports.
Ingestion points: Test failure messages and stack traces are read from cypress/reports/mochawesome.json and cypress/reports/results.xml and presented to the agent.
Boundary markers: Absent; the failure data is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.
Capability inventory: The skill has the ability to execute shell commands, read local files, and navigate directories.
Sanitization: Absent; the skill does not filter or escape the contents of the error logs before they are processed by the agent.

cypress-debugger