bamboohr
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is the official command-line interface for the Membrane platform, which acts as the provider for this skill integration.
- [COMMAND_EXECUTION]: The skill makes extensive use of the membrane CLI tool to manage authentication (membrane login), connection setup (membrane connection ensure), and action execution (membrane action run). It also allows for arbitrary API requests to the BambooHR API through the membrane request proxy.
- [INDIRECT_PROMPT_INJECTION]: The skill processes various types of employee and company data from BambooHR, creating a potential surface for indirect prompt injection if those records contain malicious instructions.
- Ingestion points: Employee directory data, training records, custom reports, and notes retrieved from the BambooHR API as documented in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided skill text.
- Capability inventory: The skill has the ability to update and create employee records, as well as perform generic HTTP requests to the BambooHR API via the membrane request command.
- Sanitization: There is no evidence of data sanitization or validation performed on the records retrieved before they are presented to the agent context.
Audit Metadata