add-mcp-resource

[Skill Scanner] Backtick command substitution detected All findings: [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] This skill is plausible and aligned with its stated purpose (generate and insert resource/resource-template code), but many example capabilities are high-privilege (reading /var/logs, returning user profile fields, writing to server.ts) and lack explicit safeguards. That makes the skill potentially dangerous in real projects: it can introduce code that exposes sensitive filesystem, database contents, or performs arbitrary network calls when executed by the server. I rate it as suspicious rather than clearly malicious: the functionality fits the purpose, but the breadth of filesystem/DB/network access and automated source modification are disproportionate without strong validation, explicit permissioning, and review steps. LLM verification: The supplied skill content does not contain explicit malicious code or obfuscation patterns in the fragment. However, it enables high-impact operations: editing server source files and performing arbitrary filesystem and network I/O in generated code. Without safeguards (review step, path and endpoint restrictions, least privilege), generated resources could expose sensitive host files or introduce exfiltration channels. Recommendation: treat generated changes as untrusted until manually reviewe