bamboohr-core-workflow-a
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external employee records and dataset definitions from the BambooHR API, which introduces a surface for indirect prompt injection if the retrieved data contains malicious instructions.\n
- Ingestion points: Employee data and metadata fetched from BambooHR API endpoints such as
POST /api/v2/datasets/{datasetName}/dataas described inSKILL.md.\n - Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate external data from the agent's internal reasoning context.\n
- Capability inventory: The skill is configured with access to file system operations including
Read,Glob,Grep,Write, andEditas listed in the YAML frontmatter.\n - Sanitization: The skill mentions schema reconciliation and encryption for data at rest, but lacks explicit sanitization or filtering logic to prevent the execution of instructions embedded within the ingested data records.\n- [EXTERNAL_DOWNLOADS]: The skill references official software development kits and documentation from BambooHR's public repositories and package registries.\n
- References official BambooHR SDKs on GitHub (
github.com/BambooHR/bhr-api-python,github.com/BambooHR/bhr-api-php) and documentation from the official developer portal.\n - Identifies the
bamboohr/apipackage on the Packagist registry for use in PHP environments.
Audit Metadata