The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions for the agent. It does not include scripts, executables, or configurations that would enable system access or network communication.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided data via the $ARGUMENTS placeholder, which serves as an ingestion point for external content. Although this represents an attack surface for indirect prompt injection, the risk is negligible because the skill does not use any tools or commands that could be abused to perform sensitive operations.
Ingestion points: User input is interpolated into the prompt via the $ARGUMENTS variable in SKILL.md.
Boundary markers: There are no explicit delimiters (e.g., XML tags or triple quotes) used to isolate the user-provided data from the agent's instructions.
Capability inventory: No tools, subprocesses, network requests, or file-writing operations are present in the skill.
Sanitization: No input validation or sanitization routines are implemented.

swot-analysis