Co-Engram/Co-Engram

C3

Self-evolving team memory

★ 10+ · Co-Engram/Co-Engram source on GitHub · this plugin in the registry

Co-Engram/Co-Engram is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes system commands, decodes base64 payloads.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
can rewrite the system promptprompt_surfacesystemPrompt
executes system commandsexec×90 in authored code, e.g. scripts/check-repo-sync.mjs:19, scripts/check-repo-sync.mjs:19
decodes base64 payloadsbase64_decode×1 in authored code, e.g. packages/core/src/graph/view-config.ts:121
starts a network servernet_server×2 in authored code, e.g. packages/viewer/src/server.ts:370, packages/claude-code-mcp/src/daemon/daemon-entry.ts:436
reads credential-class env varstoken_envANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, CO_ENGRAM_VIEWER_TOKEN

Services it injects

systemPrompt tools

Outbound domains

api.anthropic.com

Environment variables it reads

CO_ENGRAM_LANGUAGE USERPROFILE CO_ENGRAM_DEFAULT_CREATED_BY CO_ENGRAM_VIEWER_TOKEN CO_ENGRAM_DATA_ROOT CO_ENGRAM_AUTO_MEMORY_SYNC CO_ENGRAM_CLAUDE_PROJECTS_ROOT CO_ENGRAM_DAEMON_SOCKET_PATH CO_ENGRAM_PRIVATE_REPO ANTHROPIC_API_KEY

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.