The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous examples and patterns using curl, jq, and shell scripting to interact with the Buildkite API. These commands are intended for the user to execute in a terminal or automated environment for tasks such as triggering builds or creating pipelines.
[DATA_EXFILTRATION]: The skill provides patterns to send configuration and status data to api.buildkite.com and graphql.buildkite.com. As these are the official API endpoints for the skill's author (Buildkite), this represents expected functional behavior for an API integration skill.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through the processing of user-supplied data.
Ingestion points: Variable inputs such as organization slugs, pipeline names, and YAML configurations in SKILL.md and references/patterns.md are used to construct API requests.
Boundary markers: The skill does not employ explicit boundary delimiters for user-provided identifiers, although it uses jq to structure JSON payloads safely.
Capability inventory: The skill possesses the capability to perform network requests via curl and process JSON data using jq.
Sanitization: The instructions recommend local validation of YAML configurations prior to submission, but they do not define specific sanitization or filtering for all variable inputs.

buildkite-api