The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes Salesforce metadata and source code, creating a potential surface for indirect prompt injection.
Ingestion points: The skill reads metadata files including .object-meta.xml, .field-meta.xml, and .flow-meta.xml, as well as Apex source code (.cls) from the local force-app directory.
Boundary markers: No specific delimiters or instructions are used to ensure the agent ignores instructions that may be embedded within the ingested code or metadata files.
Capability inventory: The skill is configured to use Read, Write, Edit, and Bash(sf *) tools for file access and command execution.
Sanitization: The instructions do not include steps to sanitize or validate the content of the files before processing them into diagrams.

sf-diagram