salesforce-advanced-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection (Category 8).
  • Ingestion points: The skill ingests untrusted external data from Salesforce debug logs (debug.log), Apex trigger source code (ApexTrigger bodies), and EventLogFile CSV data (SKILL.md).
  • Boundary markers: There are no boundary markers or instructions to ignore embedded commands when the agent processes these external files.
  • Capability inventory: The skill utilizes Bash (Salesforce CLI and curl), Grep, and file Read operations across its troubleshooting steps.
  • Sanitization: No explicit sanitization, validation, or escaping of the ingested log contents or metadata is performed before the agent analyzes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:41 PM