reause-functions
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation includes several hooks that facilitate the ingestion of untrusted data from external sources, creating a potential vulnerability surface.
- Ingestion points: Hooks such as
useFetch(references/useFetch.md),useEventSource(references/useEventSource.md), and Firebase integrations (references/useFirestore.md, references/useRTDB.md) are designed to retrieve data from external URLs or remote databases. - Boundary markers: Absent. The provided documentation and code examples do not demonstrate the use of delimiters or specific instructions to prevent the agent from obeying commands embedded in the external data.
- Capability inventory: The documented library provides capabilities for network operations (
fetch) and dynamic script loading (useScriptTagin references/useScriptTag.md). - Sanitization: Absent. There is no explicit guidance within the skill on sanitizing, filtering, or escaping content fetched from external sources before it is processed by the agent.
Audit Metadata