The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill incorporates external input via the task_description variable. This represents a surface where untrusted data could attempt to influence the agent's planning process. However, the skill's impact is minimal as it only guides the agent to generate a markdown context map.
Ingestion points: {{task_description}} in SKILL.md.
Boundary markers: None present around the interpolated variable.
Capability inventory: No executable scripts, network access, or file-writing capabilities are defined within this skill.
Sanitization: No explicit sanitization or filtering of the task description is performed.
[SAFE]: The skill does not include any executable code, scripts, or binary files. It functions strictly as a prompt template for organizing agent thoughts.

context-map