The Agent Skills Directory

[SAFE]: The skill is a straightforward text-generation tool. It uses the disable-model-invocation: true flag, which prevents it from calling other tools or models, thereby eliminating risks associated with tool-based attacks.
[PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by interpolating user input directly into the instructions via the $ARGUMENTS variable without using boundary markers. However, due to the lack of any associated capabilities (no file, network, or command execution), this surface does not pose a security risk.
Ingestion points: The $ARGUMENTS placeholder in SKILL.md receives untrusted input from the user.
Boundary markers: Absent. User input is concatenated directly into the prompt without delimiters or instructions to ignore embedded commands.
Capability inventory: None. The skill has no access to subprocesses, file writes, or network operations.
Sanitization: None. Input is processed as raw text to inform template generation.

response-templates