superwall
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation, integration playbooks, and integration catalogs from the official Superwall domain (superwall.com) and related subdomains (webhooks.superwall.me). These are trusted vendor resources.
- [COMMAND_EXECUTION]: The skill instructs the agent to install and use the superwall CLI globally. This tool is used to manage applications, products, entitlements, and campaigns. It also provides proxies for App Store Connect and Apple Search Ads APIs, and allows running ClickHouse SQL queries against the organization's analytics data.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect instructions by ingesting documentation from the vendor's website to guide agent actions.
- Ingestion points: Documentation and integration guides are fetched via curl from superwall.com (e.g., in SKILL.md and framework-specific workflow files).
- Boundary markers: No explicit delimiters are used to separate documentation content from agent instructions.
- Capability inventory: The agent possesses shell execution capabilities through the superwall CLI, which can read, create, modify, and delete account-level resources and query analytics data.
- Sanitization: The skill does not sanitize documentation content before processing, relying on the security of the vendor's official distribution channel.
Audit Metadata