project-insights

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting data from external ServiceNow records without adequate isolation or sanitization instructions for the agent.\n
  • Ingestion points: Data is retrieved from multiple external ServiceNow tables including pm_project, pm_project_task, pm_resource_plan, rm_story, and risk (SKILL.md).\n
  • Boundary markers: The instructions lack explicit delimiters or prompts for the agent to ignore potential instructions embedded within the record data.\n
  • Capability inventory: The skill provides access to the Bash tool and specialized ServiceNow MCP query tools.\n
  • Sanitization: There is no requirement or logic provided for the agent to validate or sanitize external input before it is used to generate summary reports.\n- [COMMAND_EXECUTION]: The skill defines procedures for using the Bash tool to execute REST API requests to ServiceNow's Table API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — project-insights