The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute code at runtime to process images, specifically stating it should write a few lines against an imaging library or a command-line tool that is already installed.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from multiple sources.
Ingestion points: Source images (provided via local path or URL) and the external reference file awesome-content-campaign/references/platforms.md (as specified in SKILL.md).
Boundary markers: The instructions do not specify any boundary markers or delimiters for the external content being processed.
Capability inventory: The skill possesses capabilities to read files, download content from the network, execute shell commands/generated scripts, and write files to the disk.
Sanitization: There is no mention of sanitizing or validating the contents of the image files or the external reference markdown file before processing.
[COMMAND_EXECUTION]: The instructions explicitly guide the agent to use command-line tools available on the host system to perform image manipulation tasks.
[EXTERNAL_DOWNLOADS]: The skill is designed to download source images from arbitrary URLs provided by the user during the run, as described in the 'The run' section of SKILL.md.

awesome-content-image-adapter