skills/akillness/openmontage/remotion/Gen Agent Trust Hub

remotion

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides documentation and examples for ingesting external data via the calculateMetadata function and getInputProps API. This creates a surface where an attacker could provide data containing malicious natural language instructions designed to manipulate the AI agent's behavior during video processing.
  • Ingestion points: Example code in SKILL.md and reference.md shows calculateMetadata fetching data from /api/data and the use of getInputProps() to retrieve CLI-supplied arguments.
  • Boundary markers: The provided code snippets do not include boundary markers or explicit instructions for the model to ignore potential injection content within the fetched data.
  • Capability inventory: The skill enables significant file system influence (writing video frames, referencing static assets) and network capabilities (fetching data, rendering on AWS Lambda).
  • Sanitization: No sanitization or validation logic is present in the examples to filter or escape the content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM