The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute commands using the muapi CLI tool, specifically for authentication (muapi auth configure), image editing (muapi image edit), and monitoring predictions (muapi predict wait).
[EXTERNAL_DOWNLOADS]: The skill communicates with an external API at api.muapi.ai using curl to process image and video generation requests when CLI aliases are unavailable. This domain is associated with the skill's vendor infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from the product_name input and web search results, which are then interpolated into prompts for script and video generation.
Ingestion points: The product_name variable and data retrieved via web search tools are used to construct generation prompts.
Boundary markers: The instructions do not specify the use of delimiters or clear boundaries to separate user-provided or web-retrieved content from system instructions.
Capability inventory: The skill has the capability to execute shell commands via the muapi CLI and perform network operations using curl.
Sanitization: There is no evidence of input sanitization or validation for the product details or search results before they are processed by the LLM.

muapi-ugc-ads-workflow