contract-obligation-extraction

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official ServiceNow MCP tools and REST API endpoints to manage contract data. All operations are consistent with the stated purpose of legal obligation tracking.
  • [PROMPT_INJECTION]: The skill processes content from contract documents (via sys_attachment), which constitutes a surface for indirect prompt injection if documents contain adversarial instructions.
  • Ingestion points: Contract document content retrieved from sys_attachment (SKILL.md).
  • Boundary markers: None specified in the instructions to isolate untrusted content.
  • Capability inventory: SN-Create-Record, SN-Update-Record, and Bash for REST interactions (SKILL.md).
  • Sanitization: None specified; the skill relies on standard platform and model-level guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — contract-obligation-extraction