loomio
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the official
@membranehq/clipackage from the public npm registry, which is a vendor-owned resource used for managing integrations. - [COMMAND_EXECUTION]: The skill uses the
membranecommand-line interface to perform actions, manage connections, and proxy API requests to Loomio. - [PROMPT_INJECTION]: The skill processes data from Loomio (such as comments, polls, and discussions), which constitutes a surface for indirect prompt injection.
- Ingestion points: Data entering the context through
membrane action runandmembrane requestcommands (SKILL.md). - Boundary markers: None identified in the skill instructions.
- Capability inventory: The agent can execute shell commands via the
membraneCLI tool (SKILL.md). - Sanitization: No specific sanitization or filtering of Loomio content is described in the prompt instructions.
Audit Metadata