instantly-install-auth
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate utility for configuring authentication for the Instantly email outreach platform. It follows security best practices by instructing users to store credentials in environment variables (
.envfiles) rather than hardcoding them. All network operations target the officialapi.instantly.aidomain, which is the primary purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points where the agent processes external data, presenting a theoretical injection surface:
- Ingestion points: The skill provides TypeScript and Python templates that fetch data from
api.instantly.ai/api/v2/(specifically the/campaignsand/accountsendpoints). - Boundary markers: No specific boundary markers or delimiters are present in the provided code wrappers to separate external API data from agent instructions.
- Capability inventory: The skill involves writing local configuration files (
.env) and making outbound HTTPS requests to the service provider. - Sanitization: The provided examples perform standard JSON parsing but do not include explicit sanitization of the returned data strings.
- Risk assessment: The risk is minimal as the ingested data is used only for logging status and validation checks (e.g., verifying connection success) and is not interpolated into downstream instructions or shell commands.
Audit Metadata