The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill connects to and instructs the agent to use the Picsart MCP server at https://mcp.picsart.io/v1 and various Picsart API endpoints including api.picsart.io, video-api.picsart.io, genai-api.picsart.io, and vd-api.picsart.io for media processing and generation tasks.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing untrusted external content.
Ingestion points: User-provided text prompts, CSV data content for bulk rendering, and remote media URLs are processed via generative AI and media editing tools in files like SKILL.md and references/genai-api.md.
Boundary markers: There are no explicit delimiters or system instructions defined to prevent the agent from following commands embedded within the processed data.
Capability inventory: The skill possesses extensive capabilities to interact with external Picsart media tools, including text generation and image/video manipulation.
Sanitization: No input validation or sanitization routines are specified for handling the data interpolated into API requests.
[PROMPT_INJECTION]: The reference documentation in references/genai-api.md lists model identifiers (URNs) for speculative or future models (e.g., urn:air:openai:model:openai:gpt-5@1, urn:air:google:model:google:gemini-3-pro-preview@1). While these are likely vendor-defined routing keys for their 'AIR' service, the use of high-capability model names can influence agent behavior or user trust in the outputs.

picsart-api