The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines a workflow for generating technical documentation based on a specific template. No malicious scripts, network operations, or sensitive file accesses were detected.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to data ingestion. 1. Ingestion points: User input is captured via the $ARGUMENTS variable in SKILL.md. 2. Boundary markers: The input is not wrapped in delimiters or accompanied by instructions to ignore embedded prompts. 3. Capability inventory: The skill passes the input to the create-documentation tool. 4. Sanitization: No sanitization or validation of the task name is performed. This surface is considered low risk and consistent with the skill's primary function of processing user requests for documentation.

write-howto