cli-anything-mubu
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Mubu application, including note content, document nodes, and sync logs. This represents a surface for indirect prompt injection where malicious instructions hidden in a note could influence the agent's behavior.
- Ingestion points: The
search,show,changes, anddoc-nodescommands read data from local Mubu backups, RxDB storage, and live sync logs. - Boundary markers: The documentation recommends using the
--jsonflag for agent parsing, but it does not specify explicit delimiters or "ignore embedded instructions" warnings for untrusted content within the data payloads. - Capability inventory: The CLI includes mutation commands (
create-child,delete-node,update-text) and document access capabilities that could be targeted by an injection attack. - Sanitization: There is no documentation regarding the sanitization or filtering of note content before it is presented to the agent.
- [COMMAND_EXECUTION]: The skill defines a CLI entry point (
cli-anything-mubu) that performs operations against local databases and the live Mubu API. - The mutation commands (
mutategroup) include a safety mechanism where live edits are dry-run by default and only execute when the--executeflag is explicitly provided.
Audit Metadata