Skills/Glama/dsh

dsh@0.1.11

CAUTION· static only

Publisher claims: "Enables MCP clients to spawn and manage collaboration-style external subagents with persistent sessions, queued messaging, nested delegation limits, and shared budget/concurrency controls, plus a bilingual Windows desktop control UI." Observed in sandbox: static analysis only — behavior not yet observed.

Registry GlamaPublisher focalorsqaq · publishing for 3 daysInstalls 0Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
DEEPSEEK_API_KEYOPENAI_API_KEYConfiguration, not credentials: CODEX_APP_RUNTIME_CLI_PATH, CODEX_APP_TOOLS_PIPE_PATH, CODEX_HOME, CODEX_THREAD_ID, DEEPSEEK_BASE_URL, DSH_MCP_CONFIG, DSH_PERMISSION_MODE, DSH_RELEASE_ROOT, DSH_TELEMETRY_MODE, DSH_TEST_CODEX_EXE, DSH_UI_LOCALE, ELECTRON_RUN_AS_NODE
Where it talks to
no vendor host named in the codeAlso deepseek.com, example.test, example.invalid, gov.cn — not the publisher's domain; check what for before connecting.
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Host or code assembled from base64 fragments; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Host or code assembled from base64 fragmentssrc/multi-client.ts:109 · Host or code assembled from base64 fragmentsif (auth.session_id !== id || !timingSafeEqual(Buffer.from(auth.token, 'hex'), Buffer.from(token, 'hex'))) throw new Error('Unauthorized local connection.');Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsscripts/test-release.mjs:88 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst autoStart = await run(process.execPath,[resolve('scripts/test-ui-autostart.mjs')],{env:{...env,DSH_RELEASE_ROOT:install}});Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/test-release.mjs:92 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswriteFileSync(join(directory,'multi-client.log'), await run(process.execPath,[resolve('scripts/test-multi-client.mjs')],{env:{...env,DSH_RELEASE_ROOT:install}}));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/release/audit.mjs:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files… '/'), path.replaceAll('\\', '\\\\')]); for (const path of files) { if (/^(?:\.env(?:\.|$)|\.dsh-mcp\/|\.test-output\/|node_modules\/|upstream\/|\.release(?:-cach…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/live-models.mjs:107 · File type combined with upload action — agent may exfiltrate local data files…lse, max_depth: 0, message: 'Use your file or terminal tools to read input.json in your current directory. Sum its numbers. Create result.json with exactly the JSON object {"sum": computed sum, "count": number of entries}. Read the file ba…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/test-release.mjs:90 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswriteFileSync(join(directory,'startup-watcher.log'), await run(process.execPath,[resolve('scripts/test-startup-watcher.mjs')],{env:{...env,DSH_RELEASE_ROOT:install}}));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/test-release.mjs:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswriteFileSync(join(directory,'session-ui.log'), await run(process.execPath,[resolve('scripts/test-session-ui.mjs')],{env:{...env,DSH_RELEASE_ROOT:install}}));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/test-ui-autostart.mjs:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst environment = { ...env }; delete environment.ELECTRON_RUN_AS_NODE;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/probe-app-tools.mjs:6 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify({ app_tools_reachable: true, send_message_available: Boolean(tool), input_schema: tool?.inputSchema }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/release/archive.py:28 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif any(part in ('.git', '.dsh-mcp', '.env', '.test-output', '__pycache__') for part in relative.parts):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/test-release.mjs:91 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswriteFileSync(join(directory,'service-close-ui.log'), await run(process.execPath,[resolve('scripts/test-service-close-ui.mjs')],{env:{...env,DSH_RELEASE_ROOT:install}}));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/release/stage.mjs:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfilter: source => !['__pycache__', '.dsh-mcp', '.env'].includes(basename(source)) && !source.endsWith('.pyc'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈32 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim focalorsqaq: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  3. Host or code assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim focalorsqaqPropose a patch to the maintainer