The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and conversation history to generate diagrams. This represents a potential surface for indirect prompt injection if the processed data contains instructions designed to manipulate the agent's output. However, because the skill does not have access to any dangerous tools or system commands, the risk is negligible.
Ingestion points: Processes $ARGUMENTS and the previous conversation turn in SKILL.md.
Boundary markers: Absent.
Capability inventory: None (The skill has no associated scripts and no tool permissions).
Sanitization: Absent.
[NO_CODE]: The skill consists entirely of instructions and configuration. It does not include any executable scripts, binaries, or package dependencies.

sdo