The Agent Skills Directory

[DYNAMIC_EXECUTION]: Step 5 involves extracting C# code snippets from documentation files like README.md and building them in a temporary project. This process involves runtime compilation of source code extracted from data files to validate documentation accuracy.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from pull request titles, descriptions, and repository markdown files, which are potential ingestion points for indirect prompt injection.
Ingestion points: Metadata and content are read from PRs and markdown documentation.
Boundary markers: The instructions do not define strict delimiters or markers to prevent the agent from following instructions embedded within the ingested data.
Capability inventory: The skill has permissions to write to the file system, execute build commands, and interact with the GitHub API via the gh CLI.
Sanitization: There is no explicit sanitization or validation mentioned for the content extracted from PRs or markdown files before it is processed.
[COMMAND_EXECUTION]: The skill uses the gh CLI to perform repository actions like listing and creating draft releases. These operations use parameters derived from pull request metadata to modify the remote repository state.

publish-release