poco-ai/Agentero

C2

Unified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台;补齐 Zotero 时代的人机上下文断点。

★ 2.1k · poco-ai/Agentero source on GitHub · this plugin in the registry

poco-ai/Agentero is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It executes system commands, decodes base64 payloads, starts a network server, reads credential-class env vars.

A skill, not an installable plugin — ships SKILL.md with no plugin manifest

What it can do

CapabilityFlagEvidence
executes system commandsexec×32 in authored code, e.g. scripts/prepare-adapters.mjs:20, scripts/prepare-adapters.mjs:20
decodes base64 payloadsbase64_decode×2 in authored code, e.g. src/components/viewer/texlive/tex-live-viewer.tsx:404, src/components/viewer/texlive/render/resources.ts:21
starts a network servernet_server×1 in authored code, e.g. scripts/generate-openui-catalog.mjs:39
reads credential-class env varstoken_envGH_TOKEN, GITHUB_TOKEN

Tool registrations

0 confirmed registration point(s); analysis is incomplete.

986 source file(s) omitted by size/count/encoding limits; tool count is incomplete

Outbound domains

arxiv.org webvpn.example.edu platform.openai.com api.github.com api.atomgit.com chatgpt.com claude.ai agentero-docs.poco-ai.com openreview.net avatars.githubusercontent.com

Environment variables it reads

TAURI_ENV_TARGET_TRIPLE TAURI_ENV_PLATFORM XDG_CACHE_HOME PDFIUM_LIB_PATH GITHUB_REPOSITORY AGENTERO_ADAPTER_MAX_MB LOCALAPPDATA GH_TOKEN GITHUB_TOKEN TAG

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.