The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the bee CLI tool to perform Backlog service operations, including issue tracking, pull request management, and wiki editing.
[EXTERNAL_DOWNLOADS]: The skill references additional documentation from the vendor's official GitHub Pages site at https://nulab.github.io/bee/llms-full.txt. This resource is owned by the skill author 'nulab'.
[PROMPT_INJECTION]: The skill documents an indirect prompt injection surface but provides mitigation via clear security instructions to the agent. 1. Ingestion points: Data retrieved from Backlog projects via bee issue, bee pr, and bee wiki commands in SKILL.md. 2. Boundary markers: Explicit 'Security' section warning the agent to treat Backlog content as data, not instructions. 3. Capability inventory: Use of bee CLI for managing projects and making raw API requests in SKILL.md. 4. Sanitization: Implementation of instructional warnings to differentiate external content from agent directives.

using-bee