hunt-rce

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is explicit operational offensive guidance: it contains ready-to-run exploit payloads, PoC commands, deserialization and SSTI RCE chains, credential- and token-exfiltration techniques, container escape and supply‑chain attack instructions and persistence/practical chaining—i.e., clear instructions for deliberate system compromise and data theft.

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

• Third-party content exposure detected (high risk: 1.00). The skill's required hunting workflow instructs the agent to fetch and interpret untrusted public content (e.g., pulling CVE lists and PoCs, reading public GitHub/package.json files, probing web endpoints and OOB domains like interact.sh/oast.fun) and explicitly uses those results to choose payloads and next actions, so third‑party content can materially influence tool use.