pushover
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install
@membranehq/clifrom the NPM registry. This is a vendor-provided CLI tool used to facilitate authentication and API interactions within the Membrane ecosystem. - [COMMAND_EXECUTION]: The instructions utilize
membraneCLI commands to manage authentication, establish connections to Pushover, and execute actions. These operations are required for the skill's intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Pushover (messages, user/group data, and receipts) which could contain untrusted content.
- Ingestion points: Data retrieved from Pushover API endpoints via
membrane action runandmembrane requestin theSKILL.mdinstructions. - Boundary markers: No explicit boundary markers or instructions to ignore embedded content are provided in the skill instructions.
- Capability inventory: The skill has the capability to perform network requests via the Membrane proxy and execute actions like sending messages, managing group memberships, and cancelling notifications.
- Sanitization: No specific sanitization or escaping mechanisms for the ingested Pushover content are described.
Audit Metadata