upstash-ratelimit-ts
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for processing untrusted external data (user identifiers, IP addresses, and user agents) for the purpose of rate limiting. 1. Ingestion points: The
limit()function, documented inmethods-getting-started.mdandtraffic-protection.md, accepts dynamic input from external sources. 2. Boundary markers: The documentation does not specify the use of delimiters or validation to prevent the AI from potentially misinterpreting instructions embedded within these identifiers. 3. Capability inventory: The skill leverages network capabilities to communicate with Upstash Redis instances for state tracking. 4. Sanitization: No specific sanitization or escaping of the user-provided identifiers is described in the guidance. - [EXTERNAL_DOWNLOADS]: The documentation describes an automated feature in
traffic-protection.mdwhere the SDK retrieves IP reputation data from the well-knownipsumrepository on GitHub to maintain a global deny list.
Audit Metadata