ssti-server-side-template-injection

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs reading environment variables, application config (e.g., config['SECRET_KEY']), and files like ~/.aws/credentials for credential exfiltration, which would require the LLM/agent to handle and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is an explicit offensive playbook that provides ready-to-run SSTI/RCE payloads, webshell-writing and reverse-shell instructions, and OOB exfiltration techniques aimed at unauthorized remote code execution and data theft.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly contains templates and chains for achieving remote code execution, reading sensitive local files (e.g. /etc/passwd, ~/.aws/credentials, /proc/self/environ), and advises establishing reverse shells/persistence, which directly enables compromising a host's state.