skills/brightdata/skills/billing/Gen Agent Trust Hub

billing

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive credentials including API keys and zone passwords but provides explicit safeguards to prevent their exposure. It instructs the agent to never print keys, never ask the user to provide them in chat, and specifically warns that the /zone API endpoint returns plain-text passwords that must be discarded before reporting results to the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints (account balances and cost exports). While this constitutes a data ingestion surface, the risk is mitigated by strict read-only constraints and requirements to parse specific numeric fields rather than echoing raw data. The capability inventory is limited to network reads and budget reporting.
  • [COMMAND_EXECUTION]: The instructions reference the use of the bdata CLI tool for budget and balance queries. These commands are used for their intended primary purpose of retrieving account statistics and do not include patterns for arbitrary command execution or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 08:20 PM