The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of a local file which could potentially contain malicious instructions if the file content is modified by an external actor.
Ingestion points: The file docs/claude-reference/github-actions.md is loaded via the Read tool.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or treat embedded instructions as data rather than commands.
Capability inventory: The skill utilizes the Read tool to access file contents.
Sanitization: No sanitization or validation is applied to the content of the documentation before it is processed by the agent.

github-actions-reference