Query Standard Table

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or data exfiltration patterns were detected in the skill configuration.
  • [NO_CODE]: The skill is composed entirely of metadata and instructional text. It does not contain or reference any external scripts, binaries, or source code files.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes data retrieved from external CRM sources that could be controlled by third parties.
  • Ingestion points: CRM data fields from 'Leads', 'Meetings', 'All Contacts', and 'All Companies' tables.
  • Boundary markers: None defined within the provided skill schema.
  • Capability inventory: The skill is restricted to read-only data querying and formatting through the 'execute_action' command.
  • Sanitization: No explicit sanitization or filtering of retrieved text content is described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM