js-reverse-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes explicit examples and required outputs that embed plaintext password values (e.g., param=111111 and a curl --data-urlencode with password=111111), which would require the LLM to emit secret values verbatim in generated code/requests.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The repo includes deliberate remote-code-execution and data-exfiltration primitives (eval-ing remote messages, a persistent WebSocket RPC client that sends handler results back, and hooks that intentionally log/expose crypto keys), which constitute backdoor/RCE and credential-exfiltration capabilities.