analyzing-email-headers-for-phishing-investigation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed API keys/API tokens directly into commands (e.g., curl with "Key: YOUR_API_KEY" and "x-apikey: YOUR_VT_API_KEY"), which requires the LLM to insert secret values verbatim into generated requests/commands, an insecure pattern prone to secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow and scripts explicitly query and ingest public reputation/DNS/URL data (e.g., dig/whois and curl to AbuseIPDB, VirusTotal, URLhaus/PhishTank in Step 3 and Step 5) and the agent/script (scripts/agent.py) reads and acts on those results to generate indicators and risk decisions, so untrusted third-party content can influence its behavior.