bamboohr-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses highly sensitive Personally Identifiable Information (PII) from BambooHR, including employee names, work emails, departments, job titles, and dependent information.
  • [REMOTE_CODE_EXECUTION]: The skill requires connecting to an external MCP server at https://rube.app/mcp, which provides the logic and tool schemas for BambooHR interactions.
  • [PROMPT_INJECTION]: Risk of indirect prompt injection exists because the skill processes untrusted data from BambooHR.
  • Ingestion points: Data enters the context through tools like BAMBOOHR_GET_EMPLOYEE, BAMBOOHR_GET_TIME_OFF_REQUESTS, and BAMBOOHR_DEPENDENTS_GET_ALL.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions in HR data.
  • Capability inventory: The skill has write capabilities including BAMBOOHR_UPDATE_EMPLOYEE and BAMBOOHR_CREATE_TIME_OFF_REQUEST.
  • Sanitization: No sanitization or validation logic is specified for data retrieved from the API before it is used in subsequent operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — bamboohr-automation