irisblackwood/focus-guard

C3

Hook-level guardrails for DSH: blocks unverified edits, high-risk commands, and context-burning reads, with an auditable trail for every block.

★ 1+ · irisblackwood/focus-guard source on GitHub · this plugin in the registry

irisblackwood/focus-guard is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, runs code at install time, executes system commands, reads credential-class env vars.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./src/dsh/cordis.patch.yml
runs code at install timeinstall_scriptpostinstall: node tools/first-run-sweep.mjs
executes system commandsexec×43 in authored code, e.g. packages/core/hooks/guard.mjs:35, packages/core/hooks/guard.mjs:35
reads credential-class env varstoken_envOPENVIKING_API_KEY

Tool registrations

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

Services it injects

tools

Environment variables it reads

FG_AUDIT_FILE FG_CASE_FILE FG_SESSIONS_DIR FG_REPO_ROOT FG_WORKSPACE_FILE USERPROFILE ComSpec FG_STATUS_FILE FG_APPROVAL_DIR FG_RUN_ID

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.