collaborative-text-editor

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of documentation and reference guides for the Rivet framework. All external links and package references point to official vendor-controlled domains (rivet.dev, github.com/rivet-dev) or established package registries (npmjs.com).
  • [COMMAND_EXECUTION]: Provides standard developer commands for environment setup and debugging, such as npm install, curl for API requests, and CLI usage. These are correctly scoped to development activities.
  • [PROMPT_INJECTION]: Instructional markers like "IMPORTANT" are used appropriately for developer guidance and do not attempt to bypass AI safety constraints.
  • [DATA_EXFILTRATION]: Provides clear guidance on distinguishing between public (pk_) and secret (sk_) tokens, encouraging secure credential management practices and protecting server-side secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 12:07 AM
Security Audit — agent-trust-hub — collaborative-text-editor