web2-recon

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk offensive recon content: the guide includes explicit, repeatable techniques to discover and extract credentials/secrets (JS scraping, regex extraction, trufflehog, GitHub dorking) that can be used for unauthorized credential theft and data exfiltration; no hidden backdoor/RCE is present in the text.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime pipeline repeatedly fetches outsider-authored free text from attacker- or third-party-controlled web sources without any LLM-specific “select item” constraint (e.g., curling JSON from crt.sh and ProjectDiscovery/Chaos, then crawling and scanning resulting URLs/bodies such as with httpx/curl fallbacks and JS scanning).