building-threat-actor-profile-from-osint

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's code and workflow explicitly accept and embed API keys (e.g., X-OTX-API-KEY header, x-apikey header, and Shodan key in the URL) into requests/commands, which requires the LLM to handle or output secret values verbatim and thus poses an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and ingests public, untrusted OSINT (e.g., scripts/agent.py fetches MITRE ATT&CK from https://raw.githubusercontent.com and calls AlienVault OTX via search_alienvault_otx, while SKILL.md also specifies paste sites, social media, dark‑web forums, VirusTotal, Shodan and SpiderFoot scans) and then parses that content to build profiles and drive analyst outputs, so third‑party content can materially influence agent behavior.