workhuman-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from the Workhuman API, including recognition messages and employee names, which serves as a surface for indirect prompt injection from external sources.
  • Ingestion points: API responses from /api/v1/recognitions and /api/v1/rewards/catalog as illustrated in the skill's code examples.
  • Boundary markers: The instructions lack specific delimiters or boundary markers to distinguish between trusted instructions and potentially untrusted data from the API.
  • Capability inventory: The skill environment permits file operations (Read, Write, Edit), text searching (Grep), and restricted shell command execution (Bash for npm commands).
  • Sanitization: The implementation examples do not include sanitization or validation of the API-returned content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 10:05 AM
Security Audit — agent-trust-hub — workhuman-hello-world