instantly-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from the Instantly.ai API, such as account health metrics and campaign analytics, which are then presented to the agent.
- Ingestion points: Data is ingested from API endpoints including
/accounts/warmup-analytics,/campaigns/analytics, and/accounts/test/vitals(found in SKILL.md). - Boundary markers: There are no explicit delimiters or instructions for the agent to ignore embedded commands within the API-returned text.
- Capability inventory: The skill configuration allows
Read,Write,Edit, andBashcapabilities. - Sanitization: The skill correctly utilizes
encodeURIComponentwhen interpolating email addresses into URL paths to prevent parameter injection. - [DYNAMIC_EXECUTION]: The skill uses a standard module import to load its core API handling logic from a local file.
- Evidence: The instruction code includes
import { instantly } from "./src/instantly";to interface with the external service.
Audit Metadata