pubnub-history
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill provides patterns for processing external data from PubNub channels, which introduces a surface for indirect prompt injection.
- Ingestion points: Untrusted message data is ingested via
pubnub.fetchMessages(references/pagination-and-ordering.md) andpubnub.addListener(references/offline-catch-up.md). - Boundary markers: The implementation examples do not utilize boundary markers or explicit instructions to ignore embedded commands within the message payloads.
- Capability inventory: The skill possesses extensive data retrieval capabilities and includes the
get_pubnub_messagestool for administrative message access. - Sanitization: The provided code snippets do not demonstrate sanitization or validation of external message content before processing or display.
Audit Metadata