Plugin directory / Developer / dsh-instruction-audit
dsh-instruction-audit
Unverified 1052326311
What it does
Privacy-minimal instruction provenance receipts for DeepSeek Harness
Unverified — not yet verified
Privacy-minimal instruction provenance receipts for DeepSeek Harness Not yet verified — install and test it yourself.
“Unverified” means our automated CI has not yet installed this plugin. Feature descriptions and version compatibility are the author’s claims. This is not a security audit and not an endorsement of third-party code.
README
dsh-instruction-audit
dsh-instruction-audit records privacy-minimal receipts for the workspace
instruction files that DeepSeek Harness actually placed into a session. It is
an independent community bundle, not an official DeepSeek AI package.
It observes the durable agent-instructions message source already emitted by
the Harness. Each receipt contains the session id, event sequence/time,
baseline flag, logical scope, display path, action, and producer-owned content
digest. It never reads instruction files, stores instruction text, modifies a
workspace, or changes prompt assembly.
The published bundle has no runtime npm dependencies. It uses the existing
Cordis context supplied by the active Harness process and only imports that
type while building.
This is useful when auditing which AGENTS.md/CLAUDE.md files actually
affected a session, especially after a nested-workspace boundary or instruction
budget incident.
Install
Build a portable tarball first:
pnpm install
pnpm pack
dsh plugin --profile web add ./dsh-instruction-audit-0.1.1.tgz
The bundle writes receipts under $DSH_HOME/instruction-audit/v1/. File names
are SHA-256 hashes of session ids; the id remains inside each JSONL receipt.
Override the location without changing Harness state:
- id: instruction-audit
config:
receiptRoot: /absolute/path/to/receipts
Read one session's receipts:
dsh-instruction-audit --session session-123
Evidence Boundary
--dump-config proves only that the layer composes. A release must also be
tested by installing the packed tarball into a temporary DSH_HOME, booting a
real loopback Web profile, emitting a real durable user/message event with
the Harness agent-instructions source, observing one receipt, and confirming
that its JSONL contains no instruction body.
The plugin deliberately does not infer instructions from the filesystem. A
receipt proves only the structured source the Harness logged; it does not prove
that a model followed the instructions or that a digest is a security boundary.
Verification
Version 0.1.1 was verified against DeepSeek Harness source revision47f943859bef60e4160492346772ded9b24f765a by:
- Building the Harness production libraries and Web frontend.
- Packing this repository, then installing the tarball with
dsh plugin --profile web addinto a freshDSH_HOME. - Booting the actual loopback Web profile.
- Appending an
agent-instructionsuser message through the realSessionStorepublication path, then reading its receipt with this package's
installed CLI.
The proof used a distinct instruction-text sentinel and confirmed it was not
present in the persisted JSONL. Unit coverage also checks malformed events,
replace/remove transitions, and same-session write order.
License
MIT
Install
Install the catalog once, then DeepSeek Harness can find and install any plugin from this site automatically:
dsh plugin add dshbase-catalog Then say "install dsh-instruction-audit for me" — your agent finds it in the directory and installs it. Docs: dshbase-catalog · verified packs.
This plugin is GitHub source (not published to npm) — install it straight from the repo:
Web profile:
dsh plugin --profile web add github:1052326311/dsh-instruction-audit Headless (CLI) profile:
dsh plugin --profile headless add github:1052326311/dsh-instruction-audit Test report
Not yet L3-verified — see failure note below if we already ran it.