The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically GitHub issue bodies and local markdown files containing ticket information. This creates a surface for indirect prompt injection where instructions embedded in a ticket could attempt to influence agent behavior. However, the skill's logic is primarily focused on task metadata such as claiming, status, and priority rather than executing instructions found within the ticket content.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads local files such as tickets/store-config.md and uses path-relative lookups like ../ticket-up/references/TICKET_CONVENTION.md to determine the project's ticket convention and location. This is standard behavior for a project management tool and does not involve exfiltration of sensitive information.
[COMMAND_EXECUTION]: When a GitHub venue is specified, the skill performs network operations to query and update GitHub issues. These interactions are consistent with the skill's stated purpose of managing a remote ticket store using established service APIs.

next-ticket