hunt-dispatch

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive red-team/WAPT orchestration guide that instructs host fingerprinting and the automated loading of attack skills (SSO compromise, pre-auth RCE, credential harvesting/use, cloud IAM abuse, supply‑chain reconnaissance and exploitation), showing clear intent to perform targeted unauthorized access and likely credential/data exfiltration.

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can be ingested because step 1 fetches arbitrary runtime web content via curl -sSL ... -o /tmp/fp_body "https://$H" (public/attacker-controlled HTML and headers from target hosts), and the loader then extracts readable platform markers from that body into the agent’s context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill issues runtime curl requests (e.g., curl -sSL -m 12 -D
• -o /tmp/fp_body "https://$H" and curl -b "$SESSION_COOKIE" "https://$TARGET/api/me") and uses the fetched HTML/headers/responses to decide which platform and hunt-* skills to load, so external content directly controls agent behavior.