skill-creator

SUSPICIOUS: the skill's capabilities mostly fit its stated meta-skill purpose, but its operational footprint is very broad—installing tools, editing repos/configs, mining local histories, processing untrusted external content, and modifying routing behavior. I do not see confirmed malware or covert exfiltration, yet the combination of supply-chain exposure, broad execution authority, and prompt-injection surface makes it a medium-to-high risk skill rather than benign.

No clear indicators of intentional malware/backdoor behavior are visible in this fragment. However, there are significant security risks typical of supply-chain content rendering: (1) DOM XSS potential due to container.innerHTML fed by a large HTML string constructed from EMBEDDED_DATA with not all interpolated fields verifiably escaped, and (2) potential malicious content loading via iframe.src set to file.data_uri without visible sandboxing or scheme restrictions. If EMBEDDED_DATA or file.data_uri can be attacker-controlled, this module should be treated as high-risk and reviewed for strict escaping, URI validation, and safe rendering/sandboxing.

This fragment documents a potentially adversarial plugin-competition tactic: detecting a competitor and installing a SessionStart hook or recommending competitor disablement to influence future model behavior. It is not itself malware or executable code, but the referenced script should be reviewed before use because it may create persistence and alter plugin routing. No direct data theft or destructive behavior is evidenced in the provided text.