skills/celigo/ai/managing-users/Gen Agent Trust Hub

managing-users

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates legitimate administrative actions within the Celigo ecosystem using vendor-native CLI tools ('celigo').
  • [PROMPT_INJECTION]: Potential surface for Indirect Prompt Injection through processed user data.
  • Ingestion points: The skill reads user records from the account context via celigo users list and celigo users get <id> (SKILL.md).
  • Boundary markers: No specific delimiters or warnings to treat external user data as untrusted are included in the prompt instructions.
  • Capability inventory: The skill utilizes management commands including celigo users invite, update, and delete (SKILL.md).
  • Sanitization: Fetched data is not explicitly sanitized or validated before processing by the agent.
  • Context: This risk is considered negligible as it is inherent to the primary function of auditing and managing user accounts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:00 AM
Security Audit — agent-trust-hub — managing-users