Skills/Glama/datev-mcp

datev-mcp@0.0.1

CAUTION· static only

Publisher claims: "Connects AI assistants to the official DATEV APIs so users can query bookkeeping, payroll, and documents in plain language; any write is previewed and requires a matching one-time confirmation before it is executed." Observed in sandbox: static analysis only — behavior not yet observed.

Registry GlamaPublisher mjmirza · publishing for 6 daysInstalls 0Last detonated 6d 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
DATEV_CLIENT_SECRETConfiguration, not credentials: BASE_SHA, DATEV_CLIENT_ID, DATEV_ENV, DATEV_MCP_HOME, DATEV_MCP_NO_BROWSER, DATEV_SCOPES, PR_NUMBER
Where it talks to
datev.de (its own)
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 2026-11-08 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; 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
Access to sensitive file pathssrc/tools/files.ts:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Files a tool may send to DATEV: never hidden folders (the DATEV session, ~/.ssh, ~/.aws) and never key or secret files.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Bidirectional text override characters detectedtest/evals/run.ts:102 · Bidirectional text override characters detected — may hide content directionconst ODD_VALUES = ["ä ö ü ß", "x?y", "x#y", "%2F", "😀", "١٢٣", "a b", "x;y=z", "<script>", "'OR 1=1--", "x&y", "‮evil"];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 pathssrc/tools/files.ts:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst SECRET_NAME = /^\.env|\.(pem|key|p12|pfx|kdbx|jks)$|^id_(rsa|ed25519|ecdsa|dsa)|^credentials(\.json)?$|^session-.*\.json$/i;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandpackage.json:14 · File permission modification command — agent changes file ownership/permissions"build": "tsc && chmod +x dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known package.github/workflows/ci.yml:35 · npx invocation of non-well-known package — may execute untrusted coderun: npx -y [email protected]Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/tools/generic.ts:77 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (save_to) assertShareable(expandPath(save_to)); // never into ~/.ssh, a dotfile or a key fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/fetch-specs.sh:24 · npx invocation of non-well-known package — may execute untrusted codenpx -y [email protected] "$f" -o "$f.oas3" && mv "$f.oas3" "$f" && echo "converted $f to OpenAPI 3"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Access to sensitive file pathstest/unit/files-extf-docs.test.ts:100 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfor (const p of [join(dir, ".config", "session-sandbox.json"), join(dir, "id_rsa"), join(dir, ".env.local"), join(dir, "innocent.pdf")]) assert.throws(() => readLocalFile(p, 1000), FileError, p);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstest/unit/files-extf-docs.test.ts:98 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswriteFileSync(join(dir, ".env.local"), "X=1");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtools/check-pr-security.py:31 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈679 tok
2 files · 72 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

23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim mjmirza: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Bidirectional text override characters detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mjmirzaPropose a patch to the maintainer