cwm-tasks-generation

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions focus exclusively on legitimate project management workflows. No evidence of prompt injection, data exfiltration, or malicious code execution was found.
  • [DATA_EXFILTRATION]: The skill uses REST and MCP tools to communicate with ServiceNow instances. This network activity is consistent with the skill's purpose and targets legitimate ServiceNow API paths for record management.
  • [COMMAND_EXECUTION]: Although Bash is listed as an allowed tool in the metadata, the procedures consist entirely of API and tool interactions, and no shell commands are present in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — cwm-tasks-generation