scrivener-annotations

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interfaces with a local Python-based CLI tool (cli.py) located within the system's plugin root directory. This is a standard pattern for agent tools and does not involve untrusted remote execution.
  • [SAFE]: No prompt injection patterns, safety bypass instructions, or malicious overrides were detected in the skill's instructions or metadata.
  • [SAFE]: The skill does not perform any network operations to external domains and does not attempt to access sensitive system credentials or configuration files.
  • [SAFE]: The skill includes explicit safety protocols, such as requiring users to close the project and wait for cloud synchronization before performing modifications, which prevents accidental data loss.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:26 PM
Security Audit — agent-trust-hub — scrivener-annotations