Skills
▥AGENT LAB: SKILLS
skills/mapleshaw/yt-dlp-downloader-skill/yt-dlp-downloader/Gen Agent Trust Hub

yt-dlp-downloader

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (HIGH): The helper script scripts/download.sh is vulnerable to shell command injection. It constructs a command string containing the user-provided URL and executes it using eval. This allows an attacker to execute arbitrary shell commands by crafting a malicious URL (e.g., using command substitution).
  • DATA_EXFILTRATION (MEDIUM): The skill directs the agent to access sensitive browser cookie databases using the --cookies-from-browser flag. This exposes the user's private session data and authentication tokens.
  • EXTERNAL_DOWNLOADS (LOW): The skill requires the installation of external tools yt-dlp and ffmpeg from third-party repositories.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection through malicious video URLs. Ingestion point: Video URLs provided by the user or found in data. Boundary markers: Minimal (double quotes in script). Capability inventory: Shell execution, network access, file writing. Sanitization: None observed in the provided shell script.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 05:06 PM