Influencer

• Analyzed: May 12, 2026, 3:56 AM
• Findings: 1
• Version: 1.0.0
• Hash: e983e8c7e4656a62849a1bca89419ae472bc719d9defb6732484fa44fc47ea13
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill bundle is classified as suspicious due to the explicit instructions for the AI agent to execute shell commands and access environment variables. Specifically, `voice.md` contains `curl` commands that utilize `$ELEVENLABS_API_KEY` for external API calls and `ffmpeg` commands for local audio processing. While these actions are aligned with the skill's stated purpose of generating AI influencer content, the direct execution of shell commands introduces a significant vulnerability for potential shell injection if inputs were to be derived from unsanitized user prompts. There is no clear evidence of intentional malicious behavior such as data exfiltration or backdoor installation.