The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests SLO configuration data from external Grafana instances via the gcx CLI tool. This represents a potential surface for indirect injection from the data being managed.
Ingestion points: Data is retrieved using gcx slo definitions get and gcx resources pull as described in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded content are defined in the YAML templates or workflow instructions.
Capability inventory: The skill has the ability to execute gcx commands via Bash and manage files using the Write and Edit tools.
Sanitization: The skill does not perform explicit sanitization of the retrieved configuration data.
[COMMAND_EXECUTION]: The skill uses the gcx CLI through the Bash tool to perform operations such as listing datasources, pushing resource updates, and deleting SLO definitions. These commands are necessary for the skill's functionality and are performed using the vendor's own CLI tool.

slo-manage