gap-analysis

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill uses standard ServiceNow REST API endpoints and MCP tools for its intended purpose.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data from ServiceNow tables.
  • Ingestion points: Data is retrieved from the incident, search_log, and kb_feedback tables (including short descriptions and comments) as described in SKILL.md.
  • Boundary markers: There are no explicit markers or instructions provided to the agent to ignore or isolate instructions that may be embedded within the processed data.
  • Capability inventory: The skill has access to the Bash (native) tool and can write back to ServiceNow using the SN-Create-Record tool.
  • Sanitization: The instructions do not specify any sanitization or validation of the retrieved data before it is analyzed or used to create new knowledge submissions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — gap-analysis