reels

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires external dependencies such as mlx-whisper (via pip) and references scripts from other skills (instagram-superpower and groq-voice) for media processing and transcription.
  • [COMMAND_EXECUTION]: Executable shell scripts are used locally (scripts/transcribe_video.sh) to invoke transcription tools and system utilities like brew and pandoc for document formatting.
  • [DATA_EXFILTRATION]: The skill makes network requests to HikerAPI to fetch Instagram media metrics and user data. This behavior is documented and aligns with the skill's primary function of analyzing reference reels.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (transcribed audio from Instagram reels). While this creates a surface for indirect prompt injection, it is a standard risk for media analysis tools and no malicious intent was found in the skill's own logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 12:26 PM
Security Audit — agent-trust-hub — reels