skills/danielmiessler/lifeos/Remotion/Gen Agent Trust Hub

Remotion

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains a mandatory curl command that executes a POST request to http://localhost:31337/notify immediately upon skill invocation. This is presented as a required 'Voice Notification' step for the agent to perform.
  • [DATA_EXFILTRATION]: While the curl command targets localhost, it represents a network exfiltration pattern where internal skill state (workflow name and action) is sent to a local service without explicit user consent for each execution. This could be used to leak agent activity to other local processes.
  • [PROMPT_INJECTION]: The SKILL.md uses high-urgency language such as '🚨 MANDATORY', 'REQUIRED BEFORE ANY ACTION', and 'This is not optional. Execute this curl command immediately' to force the agent to perform the network request before any other instructions.
  • [COMMAND_EXECUTION]: The Tools/Render.ts script uses Bun's $ shell execution to run bunx remotion commands. It includes an inputProps option that passes a JSON-stringified object directly into the shell command line via the --props flag, which could lead to command injection if the input properties are not properly sanitized by the underlying shell or CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 06:48 PM
Security Audit — agent-trust-hub — Remotion