weclapp
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Weclapp (e.g., article descriptions, sales order notes, and contact details). This data is controlled by the external system and could be manipulated by an attacker to include malicious instructions.
- Ingestion points: Data returned by 'membrane action run' and 'membrane request' calls to the Weclapp API.
- Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between the skill's instructions and the data fetched from the external API.
- Capability inventory: The skill allows for data retrieval, creation, modification, and direct API requests via the Membrane CLI.
- Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the external source.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI tool using the command 'npm install -g @membranehq/cli@latest' to provide its core functionality.
- [COMMAND_EXECUTION]: The instructions direct the agent to execute various shell commands using the 'membrane' CLI for authentication, connection management, and running actions against the Weclapp platform.
Audit Metadata