collecting-open-source-intelligence

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes code examples that embed API keys/headers as string literals (e.g., "YOUR_SHODAN_API_KEY", curl -H "apikey: YOUR_KEY"), which instructs placing secrets directly into commands/code and therefore encourages the LLM to handle or emit secret values verbatim — a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and scripts/agent.py explicitly fetch and ingest untrusted public content from crt.sh, Shodan (api.shodan.io), SecurityTrails, RDAP (rdap.org), and GitHub code search and then use those results to pivot and drive further analysis/reporting, which could allow indirect prompt injection via third-party content.