wqo-account
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
scripts/wqo.shto install thewqopackage (version 0.1.1) from the official Python Package Index (PyPI) when not found locally. The installation is scoped to a project-specific virtual environment, preventing global changes. - [COMMAND_EXECUTION]: The skill invokes the CLI via a Bash runner that enforces
umask 077for file privacy and validates the tool version before execution to ensure environment integrity. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from BRAIN account messages and events, creating a potential injection surface.
- Ingestion points: Data is fetched via
wqo account messagesandwqo account eventsas described inSKILL.md. - Boundary markers:
references/runtime.mdexplicitly forbids reading credential files and requires human confirmation for alpha submissions. - Capability inventory: The skill can execute CLI commands and write local files via
wqo account snapshot. - Sanitization: Relies on mandatory human-in-the-loop verification for sensitive actions rather than automated content filtering.
Audit Metadata