The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple commands using the sf data360 CLI plugin to perform SQL queries, search operations, and metadata introspection (e.g., sf data360 query sql, sf data360 search-index list).
[COMMAND_EXECUTION]: The skill executes a Node.js script located at a specific local path: node ~/.claude/skills/orchestrating-datacloud/scripts/diagnose-org.mjs to verify org readiness.
[EXTERNAL_DOWNLOADS]: The skill documentation specifies a dependency on an 'external community sf data360 CLI plugin', which must be installed in the environment for the skill to function.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from Data Cloud SQL results.
Ingestion points: SQL query results and table descriptions enter the agent's context through sf data360 query commands in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within query results are present.
Capability inventory: The skill has access to shell command execution via the sf CLI and node subprocesses in SKILL.md.
Sanitization: There is no evidence of sanitization or filtering of the external content retrieved from Data Cloud before it is interpreted by the agent.

retrieving-datacloud