The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several local shell commands to manage observability configuration.
Evidence: Uses grep to inventory alert rules, curl for reloading local Prometheus/Alertmanager services (127.0.0.1), and docker run for testing.
Evidence: Uses environment variables ($POWERSUIT_OVERLAY) to dynamically check for and list files in local overlay directories.
[EXTERNAL_DOWNLOADS]: The skill pulls external Docker images for validation purposes.
Evidence: Downloads official images from the Prometheus organization (prom/prometheus:v3.5.0 and prom/alertmanager:v0.28.1). These are well-known and official sources for the software being configured.
[DYNAMIC_EXECUTION]: The skill executes scripts located within the project repository or generated during the workflow.
Evidence: Executes a Python-based gate check located at .github/actions/gate/run.py.
Evidence: Runs a shell script observability/alertmanager/tests/routes.sh that is expected to be part of the project's testing suite.
[INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes external configuration files.
Ingestion points: Processes Prometheus rule files (observability/prometheus/rules/*.yml) and Alertmanager configuration.
Boundary markers: None specified to differentiate between rule data and potential embedded instructions.
Capability inventory: The skill has file-write access, shell execution capabilities, Docker execution, and local network access.
Sanitization: No specific sanitization or filtering is described for the content extracted from the YAML files during the labeling or documentation steps.

alert-routes