The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to perform its core tasks.
Evidence: Use of curl for API interactions and sips or ImageMagick's convert for local image resizing in the Workflow and Quick reference sections of SKILL.md.
[DATA_EXFILTRATION]: The skill is designed to transmit local image files to a remote server (img402.dev).
Evidence: Instructions in SKILL.md guide the agent to perform curl -X POST -F image=@/path/to/image.png to external domains.
Context: This is the primary intended purpose of the skill, and the documentation provides explicit security warnings against uploading sensitive personal information or internal secrets.
[INDIRECT_PROMPT_INJECTION]: The skill presents a surface for processing untrusted data which could potentially contain malicious instructions.
Ingestion points: SKILL.md workflow instructs the agent to "Get image: Use an existing file, or generate/download one."
Boundary markers: Absent.
Capability inventory: The skill utilizes curl for network writes and sips/convert for file manipulation.
Sanitization: Absent. No specific checks are performed on the content of the image files being processed.

image-hosting