cezannehr

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes methods for retrieving and syncing employee, payroll, and time-off records from Cezanne HR, which establishes an ingestion surface for data that could theoretically contain hidden instructions.
  • Ingestion points: SKILL.md (via API calls such as apideck.hris.employees.list).
  • Boundary markers: No specific delimiters are recommended in the skill text to separate untrusted data from instructions.
  • Capability inventory: The skill utilizes network capabilities to communicate with the unify.apideck.com API and local file system access via environment variables (e.g., APIDECK_API_KEY).
  • Sanitization: No explicit sanitization or filtering logic is provided for the data retrieved from the HRIS connector.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 11:54 AM