🗑️ The original repository has been deleted or made private. This page is an archival snapshot from indexing time; the install command may no longer work.

@songjongdevsecops/wa-agent

DeepSeek Harness plugin: a wa_* tool family that lets the agent operate a WhatsApp account through a bundled Baileys bridge.

Plugin

Verification

L5 · Run tested

Verified

Risk

Out of scope

Health

Active

Trust

Silver

Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.2 · last checked 10-19Install verification details →

What it does

DeepSeek Harness plugin: a wa_* tool family that lets the agent operate a WhatsApp account through a bundled Baileys bridge.

Installation

dsh plugin --profile web add github:songjongdevsecops/wa-agent

verified

Install method: GitHub · runtime verified (L5)

Verification & Compatibility

Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.

External credentials (plugin-level): none detected

Declared DSH compatibilityfrom package.json · peerDependencies

author declared no dsh version requirement

○ The author declares no dsh version requirement — install is not blocked by version.

Install compatibility matrix (rows = plugin versions〔latest 5〕, columns = dsh versions〔latest 5〕)

At-a-glance → evidence in the cards below

plugin ＼ dsh	dsh 0.2.1-rc.2 current
bccdf2	✓

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified○ ecosystem plugin◼ ecosystem app✗ failed

bccdf2github✓ 1 runtime-verified2026-10-19

https://github.com/songjongdevsecops/wa-agent

✓dsh 0.2.1-rc.2current2026-10-19L5 · runtime verified

Environment & artifact

• Node.js: v24.14.0
• DSH: 0.2.1-rc.2
• Plugin artifact: github · https://github.com/songjongdevsecops/wa-agent (version unstated)

Levels (L1–L3 plugin-level static archive · L4/L5 newest real verdicts for this combination)

L1 static

Passed

L2 static

Passed

L3 static

Passed

L4 sandbox

Passed

L5 runtime

Passed

Install + runtime smoke verified in the dsh sandbox — installs and runs

L5 · runtime verified · valid for dsh 0.2.1-rc.2

ID: wa-agent@bccdf2@dsh0.2.1-rc.2 · profile: l4-sandbox

Issued: 2026-10-19 · expires: 2026-10-26

View checks & evidence

L1 · Found✓ Passed

Defaulted from L3L1.0_DEFAULTED_FROM_L3✓ Passed

defaulted to passed — L3 install spec passed (full-registry L3 sweep policy)

L2 · Structured✓ Passed

Defaulted from L3L2.0_DEFAULTED_FROM_L3✓ Passed

defaulted to passed — L3 install spec passed (full-registry L3 sweep policy)

L3 · Install spec✓ Passed

Install command parsedL3.1_INSTALL_COMMAND_PARSED✓ Passed

Source: registry verification · Method: install spec parse · Captured 2026-10-18

DSH version declaredL3.2_DSH_VERSION_DECLARED✓ Passed

Source: registry verification · Method: DSH version declaration · Captured 2026-10-18

L4 · Install tested✓ Passed

Install executed in confined sandboxL4.1_INSTALL_EXECUTED_CONFINED✓ Passed

Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-19

spec github:songjongdevsecops/wa-agent · channel GitHub source · outcome ran · exit 0

check took: 14.8s

Install succeededL4.2_INSTALL_SUCCESS✓ Passed

Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-19

spec github:songjongdevsecops/wa-agent · channel GitHub source · outcome ran · exit 0

check took: 14.8s

Installed artifact confirmedL4.3_ARTIFACT_CONFIRMED✓ Passed

Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-19

spec github:songjongdevsecops/wa-agent · channel GitHub source · outcome ran · exit 0

check took: 14.8s

L5 · Run tested✓ Passed

active in loader tree (150 entries)

Sandbox install passedL5.1_INSTALL_PASSED_SANDBOXED✓ Passed

Source: Windows ACL sandbox · Method: sandbox install run · Captured 2026-10-19

spec github:songjongdevsecops/wa-agent · install mode reused L4 scratch

check took: 50ms

Web boot readyL5.2_WEB_BOOT_READY✓ Passed

Source: DSH runtime · Method: web boot · Captured 2026-10-19

ready line dsh web: http://127.0.0.1:58884/?token=…

HTTP endpoint servedL5.3_HTTP_SERVED✓ Passed

Source: DSH runtime · Method: HTTP request · Captured 2026-10-19

path / · HTTP 200 · took 50ms

Plugin active in inventoryL5.4_PLUGIN_INVENTORY_ACTIVE✓ Passed

Source: DSH runtime · Method: plugin inventory query · Captured 2026-10-19

verdict active · entries 150

match: include:wa-agent · wa-agent · phase active

phases: active 122 · null 28

L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.

Author badges

Embed the official badges in your README to showcase security & install-test status:

Security Report

Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.

wa-agentAutomated review · daily

Static low, dynamic high — stricter wins → overall high.

static low→dynamic high→overall high

0 critical·0 high

highoverall · high

1static scan · vet primaryvet AST static analysis (npm artifact or git source)

Version binding

plugin versionv0.2.0dsh manifest

scanned version0.2.0git2026-10-19

current version0.2.0same version

vet verdictclean · git

Vet is an AST static scan (npm artifact or git source).

show static findings (6)

warningnetIp · networkbridge/bridge.mjs:640
httpUrl: HTTP_PORT > 0 ? `http://127.0.0.1:${HTTP_PORT}/qr.png` : null
warningnetIp · networkbridge/bridge.mjs:1539
const url = new URL(req.url ?? '/', 'http://127.0.0.1')
warningchildProcess · code-execlib/index.js:162
child = spawn(process.execPath, [bridgeFile], {
warningnetIp · networklib/index.js:236
const res = await fetch(`http://127.0.0.1:${config.httpPort}/health`, { signal: AbortSignal.timeout(2500) })
warningnetIp · networklib/index.js:244
const res = await fetch(`http://127.0.0.1:${config.httpPort}/rpc`, {
warningnetIp · networklib/index.js:378
qr = { pending: true, httpUrl: data.qr.httpUrl ?? (httpOn ? `http://127.0.0.1:${config.httpPort}/qr.png` : null) }

2dynamic auditmodel reads redacted source context · never executes plugin code

highest gradehigh

merged intooverall high

audited at2026-10-19

findings0 critical·1 high2 medium / 1 low hidden

show 4 audit findings

highUnauthenticated loopback /rpc lets any local process or web page drive the WhatsApp accountbridge/bridge.mjs:1800
The HTTP surface is enabled by default (lib/index.js Config httpPort default 29141 is always exported as WA_HTTP_PORT) and /rpc performs no token, Host or Origin check before calling handleRequest, i.e. the full method table: message.send/message.delete, chat.messages, message.download, contacts.clear, group.leave, logout, privacy.set. A malicious web page can trigger side-effecting calls with a no-CORS text/plain POST (the handler JSON-parses the body regardless of content-type), and DNS rebinding defeats the 127.0.0.1 bind to also read responses. /qr and /health additionally leak the pairing
mediumPlugin adopts any process answering /health on the configured port and sends it all RPC trafficlib/index.js:284
httpHealth() only checks res.ok on http://127.0.0.1:<httpPort>/health. A local unprivileged process that binds 29141 before the plugin starts is adopted as the 'external' bridge; every subsequent request (message text, jids, contact names, media file paths, chat queries) is sent to it and its forged responses are returned to the agent as genuine WhatsApp state. No shared secret or process identity check exists.
mediumMedia loader reads any absolute path or fetches any URL and forwards it to an arbitrary chatbridge/bridge.mjs:1570
loadMediaPayload() has no confinement to the workspace: wa_send_media / wa_profile_picture / wa_status_post accept any absolute path, read it (readFile) and send it as a WhatsApp message to a caller-chosen jid; the same function also does fetch(String(params.url)) for any URL. Because inbound WhatsApp text (including from strangers) is surfaced to the model via wa_events/wa_chat_messages, a prompt-injected agent can be steered into sending e.g. ~/.ssh/id_rsa or wa-agent/data/creds.json to an attacker's number, or into SSRF against 127.0.0.1/metadata endpoints whose body is then forwarded as me
lowWhatsApp auth-state directory and creds are created with default filesystem permissionsbridge/bridge.mjs:69
DATA_DIR (default <workspace>/wa-agent/data) is created with the process umask (typically 0755) and useMultiFileAuthState() writes creds.json/session keys with default 0644; on a multi-user host another local user can read the linked-device keys and take over the WhatsApp session.

Bundled WhatsApp bridge exposes an unauthenticated loopback /rpc that drives the whole account, and its media loader reads any absolute path / fetches any URL.

Rule: the dynamic audit can only raise risk, never lower it (raise-only, never an exemption); a wrong raise is withdrawn by human review and the tier falls back to the static verdict. Overall verdict = the stricter of the two layers.

Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.

Activity

Last commit 2026-10-18 · activity: Active

• Repo created: 2026-10-18

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/songjongdevsecops/wa-agent

Plugin notes

What is the @songjongdevsecops/wa-agent DeepSeek Harness plugin?

@songjongdevsecops/wa-agent is a DeepSeek Harness plugin maintained by @songjongdevsecops. It is cataloged on dsh.so as a Developer plugin, with a public GitHub source, declared install command, and automated static scan results; plugins static-flagged at warn or above also carry a model-driven dynamic security audit record.

How do I install @songjongdevsecops/wa-agent?

Run dsh plugin --profile web add github:songjongdevsecops/wa-agent in a DeepSeek Harness (dsh) environment. This exact command has been verified by a real install inside an isolated windows-acl sandbox (L4) plus web smoke testing (L5).

How does the security scan relate to a manual audit?

Both layers are automated, not a manual audit: the static scan is heuristic analysis of the repository source (it can produce false positives and miss context), and the dynamic security audit has a model read the harvested source context with secret files stripped and content redacted inline — plugin code is never executed. The dynamic audit only covers plugins static-flagged at warn or above, and its conclusion can only raise the combined verdict, never exempt it. Neither layer is a manual security audit or an endorsement; before using a plugin, review the repository and installed permissions, and combine both with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-10-18

@songjongdevsecops/wa-agent

What it does

Installation

Verification & Compatibility

Author badges

Security Report

Activity

Source

Author README