The Agent Skills Directory

[SAFE]: The skill instructions are focused on legitimate operational tasks related to issue tracking. There are no indications of prompt injection attempts, credential theft, or unauthorized network activity.
[SAFE]: External tool calls (list-taxonomy, search-tasks, report-bug, report-feature-request) are restricted to the One Horizon MCP environment as described in the metadata. The skill does not attempt to download or execute external code.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted user input to generate bug and feature reports. However, the capabilities are limited to record creation in a managed system.
Ingestion points: User-provided bug symptoms, feature requests, and reproduction steps (SKILL.md).
Boundary markers: Absent. The instructions do not explicitly tell the agent to use delimiters or ignore instructions embedded in user-supplied text.
Capability inventory: report-bug, report-feature-request, search-tasks, and list-taxonomy (SKILL.md).
Sanitization: Absent. The agent is instructed to use the user's input to create a markdown description for the new record.

report-issue