data360-segment

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution using the Salesforce CLI (sf) and a local Node.js diagnostic script (node ../data360-orchestrate/scripts/diagnose-org.mjs). These commands are essential for listing, creating, and publishing segments within Salesforce Data Cloud.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data from Salesforce Data Cloud, which could potentially contain malicious instructions.\n
  • Ingestion points: Results from SQL queries (sf data360 query sql) and segment metadata (sf data360 segment list) as described in SKILL.md are loaded into the agent's context from external Salesforce orgs.\n
  • Boundary markers: The instructions in SKILL.md lack boundary markers or specific guidance for the agent to distinguish between data and instructions when processing external output.\n
  • Capability inventory: The skill possesses the ability to execute shell commands and interact with the local filesystem as defined in SKILL.md.\n
  • Sanitization: No sanitization or validation logic is defined in SKILL.md for the data retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:32 PM
Security Audit — agent-trust-hub — data360-segment