The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script (scripts/run.py) that functions as a runner to send parameters to the backend API and poll for results.
[EXTERNAL_DOWNLOADS]: The runner script makes network requests to https://ai-skills.ai to execute the skill logic. This domain is consistent with the skill's documented infrastructure.
[PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data, which presents an indirect prompt injection surface.
Ingestion points: External data enters the skill via the materialUrl (user-provided URLs), materialFile (uploaded document files), and materialText (pasted content) parameters defined in references/form-schema.json.
Boundary markers: No explicit delimiting or instructions to ignore embedded commands are present in the provided local files.
Capability inventory: The skill's local capabilities are restricted to network communication with the designated API endpoint; it does not perform local file system writes or arbitrary command execution based on the processed data.
Sanitization: Input data is forwarded directly to the API without client-side sanitization or validation beyond basic JSON structure.
[SAFE]: No obfuscation, persistence mechanisms, or unauthorized credential harvesting patterns were detected. The use of an API key via environment variables follows standard security practices for this type of integration.

seo-audit