skills/getstream/agent-skills/stream/Gen Agent Trust Hub

stream

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute official getstream CLI commands for project configuration and data querying. The instructions mandate following CLI help output and confirming actions before execution.
  • [EXTERNAL_DOWNLOADS]: Data migration steps involve downloading documentation from the vendor's official getstream.io site and uploading files via curl to signed URLs, which are standard operational procedures for the service.
  • [CREDENTIALS_UNSAFE]: The skill specifically instructs the agent to handle secrets via the CLI and .env files, with explicit rules to avoid leaking them in chat, hardcoding them, or committing them to version control.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external migration data but implements boundary markers and manual confirmation steps to prevent unauthorized actions being triggered by processed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:56 PM
Security Audit — agent-trust-hub — stream