pushover
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests installing the
@membranehq/clipackage from the npm registry. This is the official tool provided by the vendor to facilitate interaction with the Membrane platform.- [COMMAND_EXECUTION]: The skill utilizes themembraneCLI to perform administrative and operational tasks, including service authentication and API request proxying.- [PROMPT_INJECTION]: The skill ingests data from external Pushover API endpoints (e.g., group details, user validation, and message statuses), which introduces a surface for indirect prompt injection. - Ingestion points: API responses processed through
membrane action runandmembrane request. - Boundary markers: The skill instructions do not specify any delimiters or safety warnings to distinguish external data from system instructions.
- Capability inventory: The skill can create and modify groups, manage user memberships, and send notifications.
- Sanitization: No explicit validation or sanitization steps are documented for the data retrieved from the Pushover API.
Audit Metadata