The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local Python script harness/scripts/ovs-notes.py using python3. This script serves as the primary logic engine, interacting with gh (GitHub CLI) and git to retrieve information. The agent is instructed to pass user-provided arguments like version strings or repository names to this script.
[EXTERNAL_DOWNLOADS]: The skill retrieves data from external GitHub repositories via the gh CLI tool. It is configured to fetch from the framework repository Rheinmir/setup by default and allows users to specify other repositories using the --repo argument.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted text from external sources, specifically release notes and git tag descriptions.
Ingestion points: Data enters the agent's context through the output of the gh release view and git tag commands executed by the underlying script.
Boundary markers: While the skill requires a source label in the header of the output, it does not explicitly define delimiters or instructions for the agent to ignore potentially malicious commands embedded within the fetched release notes.
Capability inventory: The skill has access to python3, gh, and git. The broader agent environment may contain additional tools that could be abused if the agent inadvertently follows instructions hidden in the release documentation.
Sanitization: The documentation does not specify any sanitization, filtering, or escaping of the retrieved content before it is presented to the agent.

ovs-notes