recon-and-osint

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

• Third-party content exposure detected (high risk: 0.85). The workflow’s “Passive footprint” and “Asset discovery” steps explicitly instruct fetching/using public web content at runtime (e.g., Wayback/gau, search-engine dorking, certificate transparency via crt.sh) to extract readable text/URLs that would be fed into the agent’s LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)