volcengine/OpenViking
C2Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
★ 39k+ · volcengine/OpenViking source on GitHub · this plugin in the registry
volcengine/OpenViking is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It runs code at install time, executes system commands, reads credential-class env vars, powerful capability in test/example code only.
A skill, not an installable plugin — ships SKILL.md with no plugin manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| runs code at install time | install_script | postinstall: node bin/postinstall.mjs |
| executes system commands | exec | ×8 in authored code, e.g. npm/cli/bin/ov.mjs:2, npm/cli/bin/ov.mjs:2 |
| reads credential-class env vars | token_env | AUTH_DIR, BRIDGE_TOKEN |
| powerful capability in test/example code only | dev_surface | in code that does not ship: tools/pre-execute |
| installable-looking manifest in fixtures only | dev_manifest | installable-looking manifest in fixtures only: examples/dsh-memory-plugin/package.json |
Outbound domains
docs.openviking.ai
Environment variables it reads
BRIDGE_PORT AUTH_DIR BRIDGE_TOKEN npm_config_prefix npm_config_global OPENVIKING_PLUGIN_DIR
How to read this
Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.
Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.