The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from CircleCI environments, specifically through tools that retrieve job artifacts and test metadata. This content is interpolated into the agent's context, creating a surface for potential injection attacks.
Ingestion points: Data is ingested from external sources via CIRCLECI_GET_JOB_ARTIFACTS and CIRCLECI_GET_TEST_METADATA in SKILL.md.
Boundary markers: The instructions do not define delimiters or warnings to treat CI-generated content as untrusted.
Capability inventory: The skill possesses the ability to perform write operations, such as triggering new pipelines via CIRCLECI_TRIGGER_PIPELINE.
Sanitization: There is no evidence of content sanitization or validation before the agent processes the retrieved artifact data.
[EXTERNAL_DOWNLOADS]: The skill configuration requires the addition of an external MCP server endpoint (https://rube.app/mcp). This establishes a dependency on an external service for tool execution and data processing.

circleci-automation