The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill instructs the agent to execute a Node.js script located at a relative path: node <SKILL_DIR>/../block-collection-and-party/scripts/get-block-structure.js.
Evidence: The script is used in Step 3d to fetch HTML structures for blocks like 'cards', 'tabs', 'accordion', and 'columns'.
Context: The script is part of the vendor's (Adobe) internal toolset for AEM Edge Delivery Services.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to manipulate the agent's decision-making process.
Ingestion points: Content sequences extracted from scraped web pages and a visual reference file (screenshot.png) mentioned in the prerequisites.
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the content being analyzed from the agent's instructions.
Capability inventory: The skill has the ability to execute shell commands (node) and invoke other functional skills based on its analysis.
Sanitization: There is no evidence of sanitization or validation for the incoming text or image content.

authoring-analysis