The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (gh) to query release metadata, which involves executing shell commands with potentially variable arguments derived from workflow files.
[EXTERNAL_DOWNLOADS]: The skill facilitates fetching software version information from official GitHub API endpoints, which is a standard procedure targeting well-known infrastructure.
[PROMPT_INJECTION]: The skill is designed to ingest and analyze external workflow configurations and pull request content, creating a surface for indirect prompt injection.
Ingestion points: Workflow files in the .github/workflows/ directory and pull request descriptions or comments provided by external contributors.
Boundary markers: The instructions do not define specific delimiters or instructions to isolate external data from the agent's core instructions.
Capability inventory: The agent possesses the capability to execute shell commands via the gh tool and to modify files within the repository.
Sanitization: The skill lacks explicit sanitization or validation logic for data extracted from external workflow files before processing.

github-actions