skills/remotion-dev/remotion/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage the release workflow, including process termination (SIGKILL on turbo processes), package management (npm, bun), and version control (git, gh). These are standard operations for a software release utility.
  • [DATA_EXPOSURE]: The skill retrieves sensitive credentials (NPM password and OTP) using the 1Password CLI (op). It uses these secrets to create an NPM publishing token. While this involves handling high-value secrets, the behavior is transparently documented and consistent with the skill's primary purpose of automating a developer release cycle for the authorized project owner.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to generate a changelog. This represents a potential indirect prompt injection surface.
  • Ingestion points: PR titles and authors via gh pr view, commit messages via git log, and documentation files in packages/docs/docs/ via git diff.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are present in the changelog generation steps.
  • Capability inventory: The skill possesses extensive capabilities including package publishing (npm release), file system writes (/tmp/), and network operations via standard CLI tools.
  • Sanitization: No explicit sanitization or validation of the PR titles or document content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 02:41 PM
Security Audit — agent-trust-hub — release