outbound-engine

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user for an Instantly API key and explicitly instructs running a command that embeds the key as a command-line argument (python3 scripts/instantly-audit.py --api-key ), which requires the LLM to handle and output the secret verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime includes “Phase 1: Discovery & Audit” where scripts/instantly-audit.py calls the Instantly v2 API to fetch campaigns, account inventory, and warmup/campaign performance data for inclusion in the generated audit report.