The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the @testomatio/reporter tool, specifically for initializing test runs and performing 'battle-tests' of the CI configuration locally. These commands include npx @testomatio/reporter run --remote <profile-name> and start --kind detect --format id --warn --filter ....
[REMOTE_CODE_EXECUTION]: The skill utilizes npx to download and execute the @testomatio/reporter package. This involves fetching external code from the NPM registry. As this is a resource owned by the vendor 'testomatio', it is consistent with the skill's intended functionality.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Pull Requests to populate test run metadata, creating a potential surface for indirect injection if the PR data is maliciously crafted.
Ingestion points: Pull Request titles and URLs are resolved from the CI environment and passed to the reporter tool in Step 4b.
Boundary markers: The instructions do not define explicit delimiters or 'ignore' warnings for the interpolated PR metadata.
Capability inventory: The skill environment has the capability to execute shell commands via npx and write to CI configuration files in the local repository.
Sanitization: There are no explicit sanitization, escaping, or validation steps described for the PR titles before they are assigned to the TESTOMATIO_TITLE environment variable.

setup-change-aware-pr-testing