cacheable-js
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and suggests installation of various Node.js packages from the 'cacheable' and 'keyv' ecosystems, including 'cacheable', '@cacheable/memory', and several database adapters (Redis, MongoDB, PostgreSQL, etc.). These are well-known and widely used open-source libraries for caching and storage abstraction.
- [INDIRECT_PROMPT_INJECTION]: The skill documentation describes patterns for caching and retrieving arbitrary data, which introduces a potential attack surface.
- Ingestion points: Untrusted data can enter the agent context through 'cache.get', 'cache.getMany', 'cache.getOrSet', and 'cache.wrap' operations as detailed in SKILL.md.
- Boundary markers: The instructions do not prescribe the use of boundary markers (e.g., XML tags or delimiters) to isolate retrieved cache content from the agent's instructions.
- Capability inventory: While the skill itself is a guide, the agent utilizing it may have significant capabilities like file system access or network operations.
- Sanitization: The guide lacks instructions or best practices for sanitizing or validating data before it is stored in or after it is retrieved from the cache, which could allow maliciously crafted cached content to influence the agent's behavior.
Audit Metadata