listenhub

[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] BENIGN with CAUTION: The skill/document appears coherent with its stated purpose of orchestrating media generation via scripted interfaces and internal shell scripts. It avoids direct API calls in the code fragment, relies on user-managed API keys, and provides explicit workflow guidance. However, the heavy reliance on internal scripts and persistence of credentials in shell RC files introduces risk if the scripts or host environment are compromised. The data flows are typical for a CLI-driven service dispatcher and do not reveal direct data exfiltration paths beyond generated media metadata/URLs. Overall, the footprint is proportionate to the described purpose, with moderate security risk stemming from credential persistence and opaque script behavior not inspectable in this fragment. LLM verification: Based on the provided SKILL.md alone, the skill's stated purpose (generate audio/video/images through a proprietary ListenHub API) aligns with the requested capabilities and the environment variables. However, the skill's mandatory use of locally-supplied shell scripts as the sole interface — combined with explicit instructions not to call the API directly or to second-guess script outputs — creates a high supply-chain trust requirement. Because the actual scripts are not present for inspection,