bd-cli
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with account data that may contain arbitrary content provided by users.
- Ingestion points: Data returned by the
bdCLI, such as logs, issue text, names, and descriptions (SKILL.md). - Boundary markers: The skill includes an explicit instruction to treat account data as untrusted reference material and to ignore any instructions or links embedded within it (SKILL.md).
- Capability inventory: Execution of
bdCLI commands which interact with the Bitdrift API. - Sanitization: Relies on instructions to the agent to analyze content strictly as data without executing suggested actions.
- [COMMAND_EXECUTION]: The skill uses the local
bdbinary to perform administrative and investigation tasks. This is the core functionality of the skill. - [EXTERNAL_DOWNLOADS]: The skill references documentation and installation resources from Bitdrift's official domains and GitHub repository. These are trusted vendor resources used for setup and reference.
Audit Metadata