agent-miner

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill interacts with ServiceNow tables (interaction, sys_cs_conversation, incident, etc.) using official ServiceNow MCP tools and REST API endpoints. This is consistent with the stated purpose of analyzing agent performance and automation candidates. No data is sent to non-vendor or unauthorized third-party domains.
  • [COMMAND_EXECUTION]: While the Bash tool is listed in the frontmatter, it is used locally for report generation and data processing as described in the procedure. No suspicious or privilege-escalating commands were found.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to override safety filters or disregard previous instructions. The language is purely task-oriented.
  • [EXTERNAL_DOWNLOADS]: The skill does not download external scripts, packages, or code at runtime. It relies on pre-installed MCP tools and standard ServiceNow APIs.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were found. The skill follows best practices by assuming the agent has the necessary role-based access to the ServiceNow instance.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:23 PM
Security Audit — agent-trust-hub — agent-miner