The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the index.d.ts type definition file from the official Cluster documentation site at https://docs.cluster.mu/script/index.d.ts. This is a legitimate resource for the skill's intended purpose.
[COMMAND_EXECUTION]: The skill executes local Python scripts (search.py and download.py) to manage the API definition file and perform keyword-based searches on the content.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes external documentation data.
Ingestion points: download.py fetches content from https://docs.cluster.mu/script/index.d.ts via urllib.request.
Boundary markers: No specific delimiters or "ignore instructions" warnings are added to the search results before they are presented to the agent.
Capability inventory: The skill possesses file-write (open for saving the definition), file-read (open for searching), and network-read (urllib.request) capabilities.
Sanitization: No sanitization or filtering is performed on the downloaded content beyond text parsing. However, because the source is the official documentation for the target platform and there is no automated execution of the fetched text, the risk is categorized as safe.

cluster-creator-kit-script