The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a detection script (detect-flaky-tests.ts) that uses child_process.execSync to run npm test. This is a legitimate use for the skill's primary purpose of identifying flaky tests through repeated execution.
[INDIRECT_PROMPT_INJECTION]: The skill defines logic to process test output and error messages to perform root cause analysis.
Ingestion points: In detect-flaky-tests.ts, the skill parses the output of npm test -- --reporter=json. The analyzeTest function also ingests error message strings.
Boundary markers: No specific boundary markers or instructions to ignore embedded content are present.
Capability inventory: The skill has the capability to execute shell commands via execSync.
Sanitization: The skill uses standard JSON parsing and string searching (includes) to process test data, which is appropriate for its diagnostic purpose.

flaky-test-detective