collecting-open-source-intelligence

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes code examples that embed API keys and headers directly (e.g., curl -H "apikey: YOUR_KEY" and Shodan.Shodan("YOUR_SHODAN_API_KEY")), which requires inserting and outputting secret values verbatim in commands/code and thus creates high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.95). Step 2/3/4/5 instructs runtime ingestion of outsider-authored public web/API text (e.g., crt.sh JSON, Shodan search results, Passive DNS/WHOIS outputs, SpiderFoot module results from public sources) into the agent’s LLM context via the skill’s OSINT collection workflow.