publish-element

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill automates a legitimate development lifecycle for a software project, incorporating best practices such as mandatory manual developer confirmation and automated style checks.
  • [COMMAND_EXECUTION]: The skill uses shell commands via bun, bunx, and git for package management, code formatting, and media rendering. These actions are within the expected scope of a development automation tool.
  • [EXTERNAL_DOWNLOADS]: The skill performs package installations and executions using bun, which interacts with official package registries. It also references official project documentation and asset hosting on github.com and remotion.media, both of which are vendor-controlled resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses the capability to read project source files (.tsx, .mdx) and execute shell commands. This constitutes an attack surface for indirect prompt injection; however, the risk is minimized by the skill's specific use case and requirement for human-in-the-loop validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 05:09 PM
Security Audit — agent-trust-hub — publish-element