analyzing-indicators-of-compromise

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and prerequisites show API keys inserted directly into client constructors and request headers (e.g., vt.Client("YOUR_VT_API_KEY"), headers={"Key":"YOUR_KEY"}, PyMISP(..., "API_KEY")), which encourages embedding secrets verbatim in generated code/commands and thus creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests data from public, user-contributed intelligence sources (VirusTotal, AbuseIPDB, MalwareBazaar, URLScan, Shodan and MISP) as shown in SKILL.md and implemented in scripts/agent.py, and it uses community-provided fields (reputation scores, tags, signatures, reports) to compute scores and dispositions that materially affect blocking/monitoring decisions—so untrusted third‑party content can influence agent behavior.