The Agent Skills Directory

[SAFE]: No security issues were detected in this skill. The skill is composed entirely of markdown instructions for text generation and formatting. It does not request any tools, perform any system operations, or access the network.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external technical documents and user queries, creating a potential surface for indirect prompt injection where instructions could be embedded in the retrieved content.
Ingestion points: SKILL.md instructions specify using "retrieved documents, prior messages, or tool outputs" as context.
Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore or delimit instructions found within the retrieved context.
Capability inventory: None. The skill has no file-write, network, or command execution capabilities.
Sanitization: Absent. The skill provides no mechanisms for sanitizing input data.

understand-technology