domain-osint

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs using repo/archives discovery (e.g., "github-git-recon" and "google-dorking") to find "leaked secrets" and then to "note anything that looks unintentionally exposed" in the report, which would require the LLM to capture and potentially output secret values verbatim.

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

• Third-party content exposure detected (low risk: 0.10). The required workflow ingests only provider-executed passive recon outputs from trusted tools/OSINT sources (e.g., DNS/WHOIS/CT logs/archives/GitHub repo content) based on a user-supplied domain/hostname input, and does not require reading arbitrary outsider-authored free text submitted into a queue/feed or inbox without first selecting specific items.