sevdesk
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (
@membranehq/cli) via NPM. This is a legitimate tool provided by the vendor (membranedev) to manage integrations. - [COMMAND_EXECUTION]: It uses various shell commands (
membrane login,membrane action,membrane request) to interact with the SevDesk API and manage connections. These commands are necessary for the skill's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the SevDesk API, presenting an ingestion surface for untrusted external content.
- Ingestion points: SevDesk API responses retrieved via
membrane action runandmembrane request(documented in SKILL.md). - Boundary markers: Not specified in the skill instructions.
- Capability inventory: Network requests via the Membrane proxy and action execution tools.
- Sanitization: Not explicitly defined within the skill's instruction set.
Audit Metadata