opencontext

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Documented instructions for installing the OpenContext CLI via npm (npm install -g @aicontextlab/cli). This refers to a well-known package registry and is a standard installation procedure for the described tool.
  • [COMMAND_EXECUTION]: Provides examples of shell commands for the AI agent to use (oc init, oc search, oc doc create). These are intended for project-specific context management and are within the scope of the skill's purpose.
  • [CREDENTIALS_UNSAFE]: Mentions configuring an embedding API key (oc config set EMBEDDING_API_KEY "<<your_key>>"). This is presented as a placeholder for the user and follows safe practice by not hardcoding any actual secrets.
  • [DATA_EXFILTRATION]: Documented paths such as ~/.opencontext/ and ~/.claude/commands are used for storing local application data and command definitions. There are no patterns indicating these files are sent to unauthorized external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 07:24 AM
Security Audit — agent-trust-hub — opencontext