Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →
What it doesAI
Tencent Agent Mail workbench plugin for DeepSeek Harness enabling email polling, LLM classification, archive/trash, attachment download and mail-to-agent command.
- Polling and LLM-based email classification
- Fullscreen workbench with archive/trash
- Attachment download and mail-to-agent channel
Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.
Installation
dsh plugin --profile web add github:hun1315/tencent-agent-mail-dsh-plugin#v0.2.0Install 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
Based on 1 requirement(s) across 3 @deepseek-ai/dsh-* packages. raw ranges
* ×3
✓ Running dsh 0.2.1-rc.2 is within the declared range — install is not blocked by version.
Whether it actually runs is a separate question → see the measured matrix below (L1–L5).
| plugin \ dsh | dsh 0.2.1-rc.2 current | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 | dsh 0.2.0-rc.2 | dsh 0.1.7-rc.2 |
|---|---|---|---|---|---|
| v0.2.0 | ✓ | ✓ | ✓ | ✓ | ✓ |
v0.2.0github✓ 12 runtime-verified2026-10-18
https://github.com/hun1315/tencent-agent-mail-dsh-plugin
✓dsh 0.2.1-rc.2current2026-10-18L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.2.1-rc.2 · profile: l4-sandbox
Issued: 2026-10-18 · expires: 2026-10-25
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.42026-10-16L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.2.1-alpha.4 · profile: l4-sandbox
Issued: 2026-10-16 · expires: 2026-10-23
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.22026-10-12L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.2.1-alpha.2 · profile: l4-sandbox
Issued: 2026-10-12 · expires: 2026-10-19
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.0-rc.22026-10-09L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.2.0-rc.2 · profile: l4-sandbox
Issued: 2026-10-09 · expires: 2026-10-16
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.7-rc.22026-09-26L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.7-rc.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.7-rc.2 · profile: l4-sandbox
Issued: 2026-09-26 · expires: 2026-10-03
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.7-alpha.22026-09-23L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.7-alpha.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.7-alpha.2 · profile: l4-sandbox
Issued: 2026-09-23 · expires: 2026-09-30
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.6-alpha.22026-09-20L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.6-alpha.2 · profile: l3-fullscan
Issued: 2026-09-20 · expires: 2026-09-27
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.6-alpha.12026-09-17L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.1
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.6-alpha.1 · profile: l4-sandbox
Issued: 2026-09-17 · expires: 2026-09-24
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.5-rc.22026-09-11L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.5-rc.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.5-rc.2 · profile: l4-sandbox
Issued: 2026-09-11 · expires: 2026-09-18
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.3-alpha.22026-09-08L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.3-alpha.2
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.3-alpha.2 · profile: l4-sandbox
Issued: 2026-09-08 · expires: 2026-09-15
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.1.3-alpha.12026-09-07L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.3-alpha.1
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dsh0.1.3-alpha.1 · profile: l3-fullscan
Issued: 2026-09-07 · expires: 2026-09-14
View checks & evidence
active in loader tree (151 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓prehistory2026-09-30L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: unknown
- • Plugin artifact: github · https://github.com/hun1315/tencent-agent-mail-dsh-plugin#v0.2.0
ID: tencent-agent-mail-dsh-plugin@v0.2.0@dshunknown · profile: l3-fullscan
Issued: 2026-09-30 · expires: 2026-10-07
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).
Author badges
Embed the official badges in your README to showcase security & install-test status:
`[](https://www.dsh.so/artifact/tencent-agent-mail-dsh-plugin/)``[](https://www.dsh.so/artifact/tencent-agent-mail-dsh-plugin/)``[](https://www.dsh.so/artifact/tencent-agent-mail-dsh-plugin/)``[](https://www.dsh.so/artifact/tencent-agent-mail-dsh-plugin/)``[](https://www.dsh.so/artifact/tencent-agent-mail-dsh-plugin/)``[](https://www.dsh.so/artifact/tencent-agent-mail-dsh-plugin/)`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.
Static low, dynamic medium — stricter wins → overall medium.
v0.2.0dsh manifestv0.2.0git2026-10-21v0.2.0same versionclean · gitVet is an AST static scan (npm artifact or git source).
show static findings (6)
- criticalshellExec · shell
lib/index.js:102const r = await this.runCmd([NODE, "-e", 'const{execSync}=require("child_process");process.stdout.write(execSync("npm root -g",{stdio:["igno - criticalshellExec · shell
src/runtime.js:139const r = await this.runCmd([NODE, '-e', 'const{execSync}=require("child_process");process.stdout.write(execSync("npm root -g",{stdio:["igno - warningchildProcess · code-exec
lib/index.js:44const handle = sp.spawn({ - warningnetIp · network
lib/index.js:483const r = await this.runCmd([CURL, "-s", "--max-time", String(timeoutSec || 15), "-X", "POST", "http://127.0.0.1:" + port + "/api/" + apiMet - warningchildProcess · code-exec
src/runtime.js:74const handle = sp.spawn({ - warningnetIp · network
src/runtime.js:541const r = await this.runCmd([CURL, '-s', '--max-time', String(timeoutSec || 15), '-X', 'POST', 'http://127.0.0.1:' + port + '/api/' + apiMet
show 5 audit findings
- mediumWhitelisted e-mail is turned into an agent task that executes the mail's commands
lib/index.js:531Any mail whose From matches the whitelist (email or @domain) and whose subject contains the configured keyword pushes an instruction set into a DSH executor session with full tool access; rec.subject / rec.message_id are interpolated into the prompt unescaped, so a crafted subject can add its own instructions. Guards are only autoExecute (default false), the keyword, a 10-per-hour rate limit and an advisory 'confirm destructive actions first' line; if the From header can be spoofed past Tencent's relay, this is remote command execution.
- mediumDownloaded attachment is launched with the OS handler without any type check
lib/index.js:813savedFile is derived from the attachment name / agently output and is executed by the OS handler immediately after download ('下载并打开'). A sender-controlled file name (invitation.exe, x.lnk, a.bat) is therefore run after one click, and the name is embedded in a cmd.exe command line where metacharacters are not escaped. Nothing verifies extension, signature or origin of the attachment.
- mediumFull-access filesystem writes with unvalidated path components (msgId/id)
lib/index.js:779Every write goes through a danger-full-access fs mode rooted at C:\, and path components taken from RPC args are joined without validation: invoke('download', {msgId:'..\\..\\...'}) makes ensureDirs create directories and the attachment command write outside ~/.dsh/dsh-mailbox, and purge/purge-family calls feed args.id into fileMail(id)/rmFile. Any caller able to reach the mailbox RPC (or a mail whose message_id is crafted) can therefore create/write/delete files outside the intended store.
- lowLLM API key is passed on the curl command line
lib/index.js:152The user's API key is visible in the process argument list (any local process/user with process-visibility can read it) for the duration of each autoProcess call. The request body is written to a temp file and removed, but the secret uses the argv channel.
- lowautoProcess on by default sends every new mail body to a remote LLM endpoint
lib/index.js:17Once the user creates ~/.dsh/dsh-mailbox/credentials.json, up to 3000 characters of every incoming mail (potentially containing contracts, invoices or credentials) leave the machine to whatever base_url that file names, without a per-mail prompt. The behaviour is described in the settings UI, so it is disclosed rather than covert.
Static criticals refuted as opt-in features (e-mail command dispatch, attachment auto-open); residual medium risks are path handling and full-access FS writes.
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 2026-09-04 · activity: Stable
• Repo created: 2026-09-03
• Stars: ★ 0 · Forks: 0
• Health: Stable — committed within 90 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
