performing-open-source-intelligence-gathering

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to search for and document leaked credentials and API keys (e.g., "discover leaked credentials, API keys" and "Search GitHub/GitLab for leaked secrets"), which would require extracting and potentially outputting secret values verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill explicitly guides targeted OSINT for spearphishing and credential discovery, instructs searching for leaked credentials and sensitive documents, and includes exploitation/post‑exploitation steps and persistence considerations — behaviors that enable credential theft, data exfiltration, and system compromise.

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

• Third-party content exposure detected (high risk: 0.85). The skill’s workflow is OSINT gathering (e.g., WHOIS/CT logs/subdomain enumeration, Shodan/Censys, web scraping of public sites, breach/paste-site searches), which at runtime would fetch and ingest outsider-authored free text from public web sources into the agent’s LLM context via the tool outputs/pages scraped.