instantly-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Instantly.ai API which could serve as an attack surface.
- Ingestion points: Fetches account lists, campaign analytics, and billing details via
instantly()API calls inSKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are present in the provided code snippets when processing API responses.
- Capability inventory: The skill primarily uses
console.logto output data to the agent context. - Sanitization: No explicit sanitization or validation of the API response data is performed before logging.
- [SAFE]: All external references target official Instantly.ai documentation and API endpoints (instantly.ai, developer.instantly.ai). The author Jeremy Longshore is a recognized vendor for this skill, and the provided scripts align with the stated purpose of cost optimization.
Audit Metadata