The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted data from an external environment while possessing destructive capabilities.
Ingestion points: The skill uses commands like aio aem rde logs, aio aem rde status, and aio aem rde history to retrieve data (log entries, artifact metadata) from the remote AEM environment into the agent's context.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill to protect the agent from potential instructions contained within the logs or history it reads.
Capability inventory: The skill has powerful capabilities, including aio aem rde install (deploying code/config), aio aem rde delete, and aio aem rde reset (environment modification/deletion).
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from logs before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of external components from the vendor and user-provided sources.
Plugin installation: It instructs users to install the @adobe/aio-cli-plugin-aem-rde plugin. As a vendor-owned resource, this is documented neutrally.
Artifact deployment: The aio aem rde install command supports deploying artifacts from public URLs (http/https). This is a core feature for managing RDEs and is consistent with the skill's purpose.

aem-rde