skills/neo-hack/supermario/changeset/Gen Agent Trust Hub

changeset

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard CLI tools to check the repository status and identify package names.
  • Evidence: git, sed, rg, and package manager list commands (npm, pnpm, yarn, bun) are used throughout SKILL.md.
  • [EXTERNAL_DOWNLOADS]: The skill uses package managers to run or initialize the Changesets tool, which may involve downloading the @changesets/cli package.
  • Evidence: Commands like npx changeset init are included in the instructions.
  • [PROMPT_INJECTION]: The skill reads repository configuration files as part of its normal operation, which could potentially ingest external data.
  • Ingestion points: Reads package.json and .changeset/config.json as described in SKILL.md.
  • Boundary markers: No delimiters or ignore instructions are present.
  • Capability inventory: Subprocess execution via shell commands.
  • Sanitization: No content validation is performed on the ingested configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 04:45 AM
Security Audit — agent-trust-hub — changeset