bamboohr-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to manage employee records, perform directory syncs, and generate reports within BambooHR. The access to and processing of sensitive PII (Personally Identifiable Information), compensation data, and contact details is consistent with the primary purpose of an HR management skill.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting data from the external BambooHR API and processing it within the agent context.
  • Ingestion points: Data enters the context via API calls in SKILL.md such as getDirectory(), getEmployee(), customReport(), and getTableRows().
  • Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are used when processing the retrieved data.
  • Capability inventory: The skill has access to Write, Edit, and Bash(curl:*) tools as defined in the YAML frontmatter.
  • Sanitization: There is no evidence of sanitization or filtering of external API content before it is used in logic or output.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 11:49 PM
Security Audit — agent-trust-hub — bamboohr-core-workflow-a