The Agent Skills Directory

[Prompt Injection] (LOW): Potential for indirect prompt injection through external data ingestion.
Ingestion points: Untrusted data enters the agent context via redmine_get_issue and redmine_list_issues (SKILL.md).
Boundary markers: Absent; the instructions do not provide delimiters or warnings to ignore embedded instructions in issue content.
Capability inventory: The skill possesses write capabilities including redmine_create_issue and redmine_update_issue (SKILL.md).
Sanitization: Absent; no escaping or validation of Redmine content is performed before processing.

redmine-issues