instantly-send-email

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bundled shell scripts (scripts/lead.sh, scripts/campaign.sh, scripts/email.sh, scripts/account.sh) to perform API operations. These scripts use curl for network requests and python3 for JSON processing, which are standard practices for this type of integration.- [DATA_EXPOSURE]: API keys are stored in a local configuration file at ~/.config/instantly-send-email/api_key with restricted permissions (chmod 600). The scripts also allow passing keys via environment variables or command-line arguments. Instructions explicitly warn against printing API keys and recommend rotation if a key is shared in chat.- [EXTERNAL_DOWNLOADS]: All network operations target the official Instantly API domain (api.instantly.ai). No other external downloads or remote script executions were detected.- [PROMPT_INJECTION]: The SKILL.md instructions emphasize that write actions should run in dry-run mode first and require a --send flag for actual execution, preventing the agent from performing unintended actions without user consent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:39 PM
Security Audit — agent-trust-hub — instantly-send-email