c2-evasion-methodology

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill provides guidance, methodology, and processes for analyzing and evading detection mechanisms (such as YARA, Sigma, and Snort rules) for command and control (C2) implants and beacons.

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow instructs the agent to run gh search code to search for detection rules on GitHub, which ingests outsider-authored code and repository content.