Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.5 · last checked Install verification details →
Data as of (UTC)
What it doesAI
AI film-making studio plugin that generates images and videos from text or images and breaks down short-drama scripts into prompts across six model providers.
- Text-to-image, image-to-image, text-to-video and image-to-video creation
- Short-drama script breakdown with an expert prompt generator
- Supports Agnes, DeepSeek, Qwen, Doubao, MiniMax and Ollama
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.
Trends
Four lines, four questions: total stars, stars gained this week, cumulative downloads, downloads this week. The GitHub pair comes from real-read sampling (a rotating daily shard); the npm pair from every snapshot.
6 samples (roughly every 7 days), 3 of them reconstructed (hollow dots); sampled points, not a daily series
09-17 → 10-30 · 6 points
Each bar = the delta between two samples 5–14 days apart; negative bars point down. Faint bars include reconstructed points
09-24 → 10-30 · 5 points
Reconstructed backwards from the current total using daily downloads (gaps are not interpolated)
09-17 → 10-31 · 26 points
The snapshot’s last-week rolling window (official npm + npmmirror combined)
09-17 → 10-31 · 26 points
Installation
dsh plugin --profile web add dsh-agnes-studioInstall method: npm · 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 2 @deepseek-ai/dsh-* packages. raw ranges
^0.1.0-rc.6 || ^0.2.0-rc.1 ×2
✓ Running dsh 0.2.1-rc.5 is within the declared range — install is not blocked by version.
Deciding channel: no engines.dsh declared, so every dsh* peer is checked (workspace:^ | ~ | * counts as the running version).
Whether it actually runs is a separate question → see the measured matrix below (L1–L5).
| plugin ＼ dsh | dsh 0.2.1-rc.5 current | dsh 0.2.1-rc.3 | dsh 0.2.1-rc.2 | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 |
|---|---|---|---|---|---|
| 0.7.1 | ✓ | ✓ | ✓ | ✓ | ✓ |
| v0.7.0 | · | · | · | · | · |
| 0.3.0 | · | · | · | · | · |
0.7.1npm✓ 5 runtime-verified1 failed2026-10-30
dsh-agnes-studio
✓dsh 0.2.1-rc.5current2026-10-30L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.5
- • Plugin artifact: npm · dsh-agnes-studio@0.7.1
ID: dsh-agnes-studio@0.7.1@dsh0.2.1-rc.5 · profile: l4-sandbox
Issued: 2026-10-30 · expires: 2026-11-06
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-rc.32026-10-26L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.3
- • Plugin artifact: npm · dsh-agnes-studio@0.7.1
ID: dsh-agnes-studio@0.7.1@dsh0.2.1-rc.3 · profile: l4-sandbox
Issued: 2026-10-26 · expires: 2026-11-02
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-rc.22026-10-18L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: npm · dsh-agnes-studio@0.7.1
ID: dsh-agnes-studio@0.7.1@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.42026-10-15L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: npm · dsh-agnes-studio@0.7.1
ID: dsh-agnes-studio@0.7.1@dsh0.2.1-alpha.4 · profile: l4-sandbox
Issued: 2026-10-15 · expires: 2026-10-22
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.22026-10-10L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: npm · dsh-agnes-studio@0.7.1
ID: dsh-agnes-studio@0.7.1@dsh0.2.1-alpha.2 · profile: l4-sandbox
Issued: 2026-10-10 · expires: 2026-10-17
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.22026-10-08L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.2
- • Plugin artifact: npm · dsh-agnes-studio@0.7.1
ID: dsh-agnes-studio@0.7.1@dsh0.2.0-rc.2 · profile: l5-web-smoke
Issued: 2026-10-08 · expires: 2027-01-06
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
v0.7.0github1 failed2026-09-30
https://github.com/zmm863-commits/dsh-agnes-studio
✗prehistory2026-09-30L5 · failed
- • Node.js: v24.14.0
- • DSH: unknown
- • Plugin artifact: github · https://github.com/zmm863-commits/dsh-agnes-studio#v0.7.0
ID: dsh-agnes-studio@v0.7.0@dshunknown · profile: l4-sandbox
Issued: 2026-09-30 · expires: 2026-10-07
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.3.0npm✓ 2 runtime-verified2026-09-20
dsh-agnes-studio
✓dsh 0.1.6-alpha.22026-09-20L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.2
- • Plugin artifact: npm · dsh-agnes-studio@0.3.0
ID: dsh-agnes-studio@0.3.0@dsh0.1.6-alpha.2 · profile: l4-sandbox
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.12026-09-18L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.1
- • Plugin artifact: npm · dsh-agnes-studio@0.3.0
ID: dsh-agnes-studio@0.3.0@dsh0.1.6-alpha.1 · profile: l3-fullscan
Issued: 2026-09-18 · expires: 2026-09-25
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.
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 dsh.so badges in your README to show this plugin's automated security-scan and install-test status:
`[](https://www.dsh.so/artifact/dsh-agnes-studio/?ref=badge)``[](https://www.dsh.so/artifact/dsh-agnes-studio/?ref=badge-install)``[](https://www.dsh.so/artifact/dsh-agnes-studio/?ref=badge-install)``[](https://www.dsh.so/artifact/dsh-agnes-studio/?ref=badge-install)``[](https://www.dsh.so/artifact/dsh-agnes-studio/?ref=badge-install)`dsh.so is an independent community project, not affiliated with or endorsed by DeepSeek AI. Badges are maintained by dsh.so; embed links carry a ?ref= attribution parameter.
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 critical (authoritative when present) → overall critical.
v0.7.1dsh manifest0.7.1npm2026-11-010.7.1same versionclean · npmVet is an AST static scan (npm artifact or git source).
show static findings (4)
- criticalshellExec · shell
lib/index.js:57function exec(cmd, args, timeoutMs = 6e5) { - criticalshellExec · shell
lib/index.js:125const r = await exec(cmd, ["-version"], 15e3); - criticalshellExec · shell
lib/index.js:150const r = await exec(cmd, ["-version"], 1e4); - warningchildProcess · code-exec
lib/index.js:61child = spawn(cmd, args, { windowsHide: true });
show 6 audit findings
- criticalUnauthenticated /localfiles/upload writes any file at any path (path traversal via body filename)
lib/index.jsThe filename is taken verbatim from the JSON body and joined to LOCALFILES_DIR without basename()/prefix validation, so filename="../../../home/user/.bashrc" (or any other file) writes attacker-controlled content anywhere the host process can write — a direct path to code execution/persistence. No authentication is required and wildcard CORS lets any visited web page trigger it.
- criticalProxy honors client-supplied baseUrl and sends the vendor API key to it (key exfiltration + SSRF)
lib/index.jsgetVendorBaseUrl returns customUrl whenever it is supplied, so a caller can set baseUrl to an attacker host (or an internal address) while the host still attaches the resolved vendor credential as an Authorization header. Result: theft of Agnes/DeepSeek/Qwen/Doubao/MiniMax keys, plus unrestricted SSRF from the host (localhost services, cloud metadata).
- highAll /agnes-studio/api routes are unauthenticated with Access-Control-Allow-Origin: *
lib/index.jsThere is no token/session check on the handler, and the preflight is answered with 204 while allowing the Content-Type header. Any web page the user opens can therefore read responses from and issue state-changing POSTs to the local DSH server, which is the precondition that makes the file-write, proxy and SSRF issues remotely exploitable.
- high/ohstory routes take an arbitrary root and can read or write .md/.txt/.json/.yaml anywhere
lib/index.jssafeJoin only prevents escaping the caller-chosen root; the root itself is attacker-controlled, so readText can read any .json/.yaml/.md/.txt file on the filesystem (e.g. application configs and stored secrets) and writeText/createProject can create directories and overwrite such files anywhere. The extension whitelist limits but does not remove the impact.
- mediumanchor 'materialize' fetches an arbitrary caller-supplied URL (blind SSRF)
lib/index.jsFor a non-data body.image/body.clip value the host performs a GET to any http(s) URL the caller provides, without host restriction, letting a remote caller probe internal services or trigger side-effecting GET endpoints; the response body is written to disk but not returned, so the impact is blind and primarily a reachability/abuse channel.
- lowWeChat AppSecret stored in plaintext under the shared temp directory
lib/index.jsdataRoot() is tmpdir()/dsh-agnes-studio, created with default permissions; on multi-user machines with a typical umask the secret file is readable by other local users. The API itself only returns has_secret, so this is a local hardening gap rather than a remote leak.
Unauthenticated HTTP routes allow arbitrary file write/read and forwarding of the vendor API key to an attacker-chosen baseUrl; wildcard CORS makes this reachable from any web page.
Rule (2026-10-28): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); the static scan tier (vet primary, dsh backstop) applies only when there is none (not queued / audit failed / withdrawn). The audit never writes the exemption list (exemptions are manual only); a wrong conclusion is withdrawn by human review and the tier falls back to the static scan tier.
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 2026-10-04 · activity: Active
• Repo created: 2026-09-15
• Stars: ★ 25 · Forks: 5
• Health: Active — committed within last 30 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).
Frequently asked questions
What is dsh-agnes-studio?
dsh-agnes-studio is a DeepSeek Harness (dsh) plugin listed on dsh.so — an independent community registry that indexes public source repositories and publishes automated security-scan and install-verification results for each entry.
Is dsh.so or this plugin page official?
dsh.so is an independent community registry and is not affiliated with, endorsed by, or sponsored by DeepSeek AI.
How do I install dsh-agnes-studio?
Run dsh plugin --profile web add dsh-agnes-studio in a DeepSeek Harness (dsh) environment. That exact command passed a real install inside an isolated 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, so it can produce false positives and miss context. The model-driven dynamic security audit only covers plugins static-flagged at warn or above, never executes plugin code, and its conclusion is authoritative when there is one (it may raise or lower the static tier); exemptions stay manual. Neither layer is an endorsement: review the repository and the permissions it asks for before installing, together with the verification level and health signals.
How fresh is the data on this page?
The data on this page is as of 2026-11-01 (UTC) — the most recent valid timestamp among the registry refresh, install verification, security scan and dynamic audit. Build time is never used as a data date.