skills/serac-labs/serac/cmdb-patterns/Gen Agent Trust Hub

cmdb-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates an attack surface for indirect prompt injection as it ingests data from a remote ServiceNow instance and provides write capabilities to that environment.
  • Ingestion points: Configuration Item (CI) data is retrieved from ServiceNow via tools such as snow_cmdb_search, snow_query_table, and snow_get_ci_details (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to treat data retrieved from external fields as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill utilizes powerful write operations, including snow_create_ci, snow_create_ci_relationship, and snow_cmdb_identify_reconcile (SKILL.md).
  • Sanitization: No explicit validation or sanitization routines are provided for handling CI names, descriptions, or other metadata retrieved from the CMDB before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:16 PM
Security Audit — agent-trust-hub — cmdb-patterns