agency-clients

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements multi-tenancy safeguards by instructing the agent to explicitly map accounts to clients and confirm the target client before performing any publishing or destructive actions.
  • [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were detected in the instructions.
  • [SAFE]: The tool calls mentioned (e.g., get_me, list_accounts, bulk_create_posts) are consistent with the skill's stated purpose and the author's platform (PostEverywhere).
  • [SAFE]: The instructions include robust data separation practices, such as filtering reports by account or campaign IDs to ensure one client's data is never visible to another.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:09 PM