The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several templates and examples containing shell commands such as npm install, mkdir, curl, lsof, and kill. These are strictly instructional examples intended for inclusion in tutorials written by the user and do not pose a risk of execution by the agent during its operation.
[INDIRECT_PROMPT_INJECTION]: The skill is instructed to read from .agents/developer-audience-context.md to customize its output. This file represents an external data ingestion point that could potentially contain malicious instructions, though it is a standard mechanism for context sharing within the platform.
[DATA_EXPOSURE]: The skill accesses the local agent context file .agents/developer-audience-context.md. This is a legitimate use of internal configuration data to improve the relevance of the generated content.

technical-tutorials