The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process external files to generate technical documentation.- Ingestion points: Uses the Read, Glob, and Grep tools to retrieve content from files for processing.- Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore potentially malicious embedded commands within the source material.- Capability inventory: The skill has permissions to create and modify the filesystem using Write and Edit tools.- Sanitization: No explicit sanitization or validation logic is defined to handle malicious input during the document generation process.- [COMMAND_EXECUTION]: The skill's documentation templates include instructional examples of shell commands such as npm install, kubectl logs, and curl for API requests. These are static text examples intended for technical documentation output and are not executed by the skill itself.

technical-writing