sf-datacloud-act

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the sf CLI with the data360 plugin to perform activation and data action management tasks within a Salesforce environment.
  • [DYNAMIC_EXECUTION]: The skill executes a Node.js script located at ~/.claude/skills/sf-datacloud/scripts/diagnose-org.mjs to classify organizational readiness before performing state-changing operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect injection through the ingestion of external JSON configuration files.
  • Ingestion points: Commands in SKILL.md ingest files such as target.json, activation.json, and action.json using the -f flag.
  • Boundary markers: The instructions do not define specific boundary markers or 'ignore' instructions for the content of these processed files.
  • Capability inventory: The skill has the capability to execute shell commands and Node.js scripts which could be targeted by malformed file content.
  • Sanitization: There is no mention of sanitizing or validating the JSON content before it is passed to the CLI tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:48 PM
Security Audit — agent-trust-hub — sf-datacloud-act