rde
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various untrusted sources, including warehouse tables, user-uploaded CSV files, and external business logic artifacts such as code, spreadsheets, or documents (as seen in
playbooks/extract-business-logic.md). - Ingestion points: Untrusted data enters the agent's context through tools like
mb query,mb table get, and theWebFetchtool used for fetching business logic artifacts. - Boundary markers: The skill uses instruction-based constraints (e.g., 'read nothing else', 'follow it') and structured JSON delimiters for command inputs, though explicit safety boundary markers for data interpolation are not consistently applied across all playbooks.
- Capability inventory: The agent has access to
Bash,Write,Edit, andWebFetch, allowing it to execute commands, modify the filesystem, and make network requests based on its analysis of potentially malicious data. - Sanitization: The skill emphasizes using the
--jsonflag andjqfor parsing CLI outputs, which helps in structured data handling, but the natural language processing of external documents lacks formal sanitization. - [DYNAMIC_EXECUTION]: The skill dynamically generates an executable bash script (
./.scratch/q) to facilitate warehouse queries. - Evidence: In
references/state.md, the skill usescat > ./.scratch/q <<'SH'andchmod +x ./.scratch/qto create and set permissions for a helper script that wrapsmb querycalls. This script is then executed throughout the playbooks. - [COMMAND_EXECUTION]: The skill makes extensive use of the
Bashtool to interact with the system and themb(Metabase) CLI. This includes creating directories (mkdir -p ./.scratch), managing files, and executing complex query commands. - [EXTERNAL_DOWNLOADS]: The skill recommends the installation of external software and scripts.
- Evidence:
README.mdandSKILL.mdsuggest installing@metabase/clivianpmand adding the skill itself usingnpx skills add metabase/agent-skills. These resources are provided by the vendor (Metabase) and are documented neutrally.
Audit Metadata