The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use shell commands like curl, wc, and ffprobe to manage media files and interact with the Sync Labs API.
[DATA_EXFILTRATION]: The skill performs network operations to api.sync.so to upload media assets. These operations are directed to the vendor's own infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied scripts and external media URLs, creating a surface for indirect prompt injection.
Ingestion points: User-provided speech scripts and public media URLs in SKILL.md and references/media-input.md.
Boundary markers: None; the instructions do not specify how to delimit user input from agent instructions.
Capability inventory: The skill uses tool calls and shell commands to transmit processed content to an external API.
Sanitization: No explicit sanitization or validation of the input content is required by the instructions.
[EXTERNAL_DOWNLOADS]: The documentation references official vendor packages including syncsdk and @sync.so/mcp-server for system setup and connection.

talking-photo