The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the sau (social-auto-upload) CLI tool to log in, check account status, and upload video files.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided strings (title, description, tags) and interpolates them into command-line arguments. This presents a potential surface for command injection if inputs are not properly sanitized or quoted by the agent, though the documentation provides examples using double quotes for mitigation.
Ingestion points: User-provided title, description, and tags strings used in the upload-video command.
Boundary markers: The skill documentation uses double quotes around string arguments in examples.
Capability inventory: Execution of shell commands via the sau utility.
Sanitization: No specific sanitization or validation logic is explicitly defined within the skill instructions beyond the example usage.

weibo-upload