The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to use command-line tools such as curl to perform REST API operations for the creation and management of Service Level Objectives.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data structures during the translation of Datadog SLOs, which creates a potential surface for indirect prompt injection if the source data is malicious.
Ingestion points: references/datadog-migration.md contains instructions for ingesting and translating Datadog SLO JSON definitions.
Boundary markers: The documentation does not specify the use of delimiters or specific warnings to ignore instructions embedded within the processed JSON data.
Capability inventory: The skill employs curl for network operations and utilizes shell access to interact with the KubeSense API.
Sanitization: No explicit logic or instructions for sanitizing the input data from Datadog are provided before processing the payloads.

kubesense-slo