The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the glab CLI tool to perform repository operations, including viewing, creating, and updating issues, as well as making direct GitLab API calls. These commands are executed locally using the user's existing GitLab authentication.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted data from external sources that can then influence the agent's behavior.
Ingestion points: Reads the content of a GitLab parent issue using the glab issue view command (specified in SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the retrieved issue body.
Capability inventory: The agent has the capability to create and update issues on GitLab via glab commands and API calls (specified in SKILL.md).
Sanitization: There is no explicit sanitization or filtering of the content retrieved from the GitLab issue before it is processed by the model.
Mitigation: The skill includes a mandatory human-in-the-loop checkpoint, requiring the user to approve the proposed plan and phases before any issues are created or updated.

codely-plan-create-gitlab