create-render-profile

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically assembles and executes shell commands for ffmpeg, ffprobe, stat, and awk using the Bash tool. These commands are generated based on user-provided inputs like profile names and target resolutions to process video samples.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection or command injection by interpolating user-supplied strings directly into shell command templates.
  • Ingestion points: User-provided profile names and sample video file paths defined in SKILL.md.
  • Boundary markers: The skill includes an explicit instruction to show the exact command to the user before execution, serving as a manual security boundary.
  • Capability inventory: The skill uses Bash for media processing and Write for saving JSON profiles, both of which are scoped to the plugin's data directory.
  • Sanitization: Profile names are slugified to prevent basic injection, but the skill lacks instructions for escaping or validating the sample file path interpolated into the -i flag of ffmpeg commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:34 PM
Security Audit — agent-trust-hub — create-render-profile