The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of a local shell script named cf-assets.sh. The agent is instructed to find this script on the filesystem and execute it with arguments for uploading, listing, or deleting files.
[DATA_EXFILTRATION]: The skill's primary function is to transmit local data (files, images, videos) to an external third-party domain assets.yesy.site. This domain is not recognized as a trusted vendor or well-known service in the provided security context.
[EXTERNAL_DOWNLOADS]: The skill references an external API and documentation hosted at https://assets.yesy.site/docs.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing arbitrary user-provided files that are then handled by a local script and transmitted over the network.
Ingestion points: Local files identified by user-provided paths (e.g., ~/Downloads/photo.jpg) in the upload command.
Boundary markers: The skill does not define specific boundary markers or 'ignore' instructions for the content of the files being processed.
Capability inventory: The skill has the ability to execute bash scripts (cf-assets.sh) and perform network requests (REST API) via curl or similar tools within the script.
Sanitization: No evidence of content sanitization or file validation is present in the skill instructions.

cloudflare-assets