The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell-level commands using the muapi CLI tool, including muapi image generate, muapi image edit, and muapi auth configure.
[EXTERNAL_DOWNLOADS]: The skill uses curl to perform POST requests to an external endpoint (https://api.muapi.ai/api/v1/<endpoint>) and interacts with muapi predict wait for long-polling, involving network operations to a specialized third-party service.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface where untrusted user input is interpolated into downstream actions.
Ingestion points: The brief and brand_style inputs are gathered from the user in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions to the LLM to ignore potentially malicious content embedded within these inputs.
Capability inventory: The skill has the capability to perform network requests via curl and execute muapi CLI tools.
Sanitization: There is no evidence of sanitization, escaping, or validation of the brief or brand_style inputs before they are included in image generation prompts or API request bodies.

muapi-instagram-post