The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Gitee repositories, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data enters the agent context through list_repo_issues and search_open_source_repositories tools as described in SKILL.md.
Boundary markers: The skill includes process boundaries by requiring the agent to "Clarify the Issue Content" and "Confirm with the user before creating," which helps mitigate accidental execution of embedded instructions.
Capability inventory: The skill possesses the ability to write to the repository via create_issue and read from it via list/search tools.
Sanitization: No explicit automated sanitization of external issue content is described beyond the human-in-the-loop confirmation step.

create-issue